A Sequence Modelling Approach to Question Answering in Text-Based Games

Question-answering systems are recognized as popular and frequently effective means of information seeking on the web. In such systems, information seekers can receive a concise response to their queries by presenting their questions in natural language. Interactive question answering is a recently proposed and increasingly popular solution that resides at the intersection of question answering and dialogue systems . On the one hand, the user can ask questions in normal language and locate the actual response to her inquiry; on the other hand, the system can prolong the question-answering session into a dialogue if there are multiple probable replies, very few, or ambiguities in the initial request. By permitting the user to ask more questions, interactive question answering enables users to interact with the system and receive more precise results dynamically. This survey offers a detailed overview of the interactive question-answering methods that are prevalent in current literature. It begins by explaining the foundational principles of question-answering systems, hence defining new notations and taxonomies to combine all identified works inside a unified framework. The reviewed published work on interactive question-answering systems is then presented and examined in terms of its proposed methodology, evaluation approaches, and dataset/application domain. We also describe trends surrounding specific tasks and issues raised by the community, so shedding light on the future interests of scholars. Our work is further supported by a GitHub page synthesizing all the major topics covered in this literature study. https://sisinflab.github.io/interactive-question-answering-systems-survey/

In this introduction, we present our overview of interactive question answering (IQA). We contextualize IQA in the wider field of question answering, and establish connections to research in Information Retrieval and Dialogue Systems. We highlight the development of QA as a field, and identify challenges in the present research paradigm for which IQA is a potential solution. Finally, we present an overview of papers in this special issue, drawing connections between these and the challenges they address.

Evaluating interactive question answering (QA) systems with real users can be challenging because traditional evaluation measures based on the relevance of items returned are difficult to employ since relevance judgments can be unstable in multi-user evaluations. The work reported in this paper evaluates, in distinguishing among a set of interactive QA systems, the effectiveness of three questionnaires: a Cognitive Workload Questionnaire (NASA TLX), and Task and System Questionnaires customized to a specific interactive QA application. These Questionnaires were evaluated with four systems, seven analysts, and eight scenarios during a 2-week workshop. Overall, results demonstrate that all three Questionnaires are effective at distinguishing among systems, with the Task Questionnaire being the most sensitive. Results also provide initial support for the validity and reliability of the Questionnaires.

Online services often require users to agree to lengthy and obscure Terms of Service (ToS), leading to information asymmetry and legal risks. This paper proposes TOSense—a Chrome extension that allows users to ask questions about ToS in natural language and get concise answers in real time. The system combines (i) a crawler "tos-crawl" that automatically extracts ToS content, and (ii) a lightweight large language model pipeline: MiniLM for semantic retrieval and BART-encoder for answer relevance verification. To avoid expensive manual annotation, we present a novel Question Answering Evaluation Pipeline (QEP) that generates synthetic questions and verifies the correctness of answers using clustered topic matching. Experiments on five major platforms, Apple, Google, X (formerly Twitter), Microsoft, and Netflix, show the effectiveness of TOSense (with up to 44.5% accuracy) across varying number of topic clusters. During the demonstration, we will showcase TOSense in action. Attendees will be able to experience seamless extraction, interactive question answering, and instant indexing of new sites.

Vision-and-language navigation is a newly emerging research topic developing rapidly in recent years, and it is one of the representative research tasks in the frontier field of vision-language interaction. The goal of this task is to realize autonomous navigation based on visual perception of environment according to language instructions given by human. This paper reviews the recent progress in vision-and-language navigation. Firstly, the research content of this task is introduced, and the three main problems and challenges of cross-modal semantic alignments, semantic understanding and reasoning, and generalization ability enhancement are analyzed. Secondly, commonly-used datasets and evaluation metrics are listed. Thirdly, the research progress of this task is summarized from four aspects of imitation learning, reinforcement learning, self-supervised learning and other methods, and the effects of the typical solutions are carefully compared and analyzed. Fourthly, the current research trends of this task are discussed, which mainly include continuous environment navigation, advanced complex instruction comprehension and common sense reasoning. Finally, the future development directions such as 3D visual-and-language navigation, embodied question answering and interactive question answering are further discussed and prospected.

Policy learning is an active topic in dialogue systems research, but it has not been explored in relation to interactive question answering (IQA). We take a first step in learning adaptive interaction policies for question answering : we address the question of how to acquire enough reliable query constraints, how many database results to present to the user and when to present them, given the competing trade-offs between the length of the answer list, the length of the interaction, the type of database and the noise in the communication channel. The operating conditions are reflected in an objective function which we use to derive a hand-coded threshold-based policy and rewards to train a reinforcement learning policy. The same objective function is used for evaluation. We show that we can learn strategies for this complex trade-off problem which perform significantly better than a variety of hand-coded policies, for a wide range of noise conditions, user types, types of DB and turn-penalties. Our policy learning framework thus covers a wide spectrum of operating conditions. The learned policies produce an averagerelativeincrease in reward of 86.78% over the hand-coded policies. In 93% of the cases the learned policies perform significantly better than the hand-coded ones (p< .001). Furthermore we show that the type of database has a significant effect on learning and we give qualitative descriptions of the learned IQA policies.

Background White matter hyperintensities (WMH) are considered to contribute to diminished brain reserve, negatively impacting on stroke recovery. While WMH identified in the chronic phase after stroke have been associated with post-stroke aphasia, the contribution of premorbid WMH to the early recovery of language across production and comprehension has not been investigated. Objective To investigate the relationship between premorbid WMH severity and longitudinal comprehension and production outcomes in aphasia, after controlling for stroke lesion variables. Methods Longitudinal behavioral data from individuals with a left-hemisphere stroke were included at the early subacute (n = 37) and chronic (n = 28) stage. Spoken language comprehension and production abilities were assessed at both timepoints using word and sentence-level tasks. Magnetic resonance imaging (MRI) was performed at the early subacute stage to derive stroke lesion variables (volume and proportion damage to critical regions) and WMH severity rating. Results The presence of severe WMH explained an additional 18% and 25% variance in early subacute (t = −3.00, p = .004) and chronic (t = −3.60, P = .001) language comprehension abilities respectively, after controlling for stroke lesion variables. WMH did not predict additional variance of language production scores. Conclusions Subacute clinical MRI can be used to improve prognoses of recovery of aphasia after stroke. We demonstrate that severe early subacute WMH add to the prediction of impaired longitudinal language recovery in comprehension, but not production. This emphasizes the need to consider different domains of language when investigating novel neurobiological predictors of aphasia recovery.

We propose a novel scalable Web portal called LSOMP (Large Scale Ordinance Mining Portal) to analyze ordinances and their tweets (of the order of thousands and millions). It entails commonsense knowledge (CSK) and natural language processing (NLP), disseminating ordinance-tweet mining results via interactive graphics and Question Answering (QA).

This paper explains the research and design of the experimental teaching system of civil engineering. Teachers, students and administrators can use this APP to access and manage teaching resources, and interact with each other in real time through interactive answering module. The system is mainly developed by Android Studio and it adopts the idea of layered design. It includes two bottom modules: network communication and message push, and five functional modules: experiment arrangement, job management, interactive question answering, user management and setting. After testing, the experimental teaching management system can meet the functional needs of users. The design of Android course teaching system provides a good reference for the development of similar courses, and achieves the expected development purpose.

Some of the Follow-Up Questions (FU Q) that an Interactive Question Answering (IQA) system receives are not topic shifts, but rather continuations of the previous topic. In this paper, we propose an empirical framework to explore such questions, with two related goals in mind: (1) modeling the different relations that hold between the FU Q's answer and either the FU Q or the preceding dialogue, and (2) showing how this model can be used to identify the correct answer among several answer candidates. For both cases, we use Logistic Regression Models that we learn from real IQA data collected through a live system. We show that by adding dialogue context features and features based on sequences of domain-specific actions that represent the questions and answers, we obtain important additional predictors for the model, and improve the accuracy with which our system finds correct answers.

Personalized online learning has been significantly adopted in recent years and become a potential instructional strategy in online learning. The promising way to provide personalized online learning is personalized recommendation by navigating students to suitable learning contents at the right time. However, this is a nontrivial problem as the learning environments are considered as a high degree of flexibility as students independently learn according to their characteristics, and situations. Existing recommendation methods do not work effectively in such environment. Therefore, our objective of this study is to provide personalized dynamic and continuous recommendation for online learning systems. We propose the method that is based on the contextual bandits and reinforcement learning problems which work effectively in a dynamic environment. Moreover, we propose to use the past student behaviors and current student state as the contextual information to create the policy for the reinforcement agent to make the optimal decision. We deploy real data from an online learning system to evaluate our proposed method. The proposed method is compared with the well-known methods in reinforcement learning problems, i.e. $$\varepsilon$$ -greedy, greedy optimistic initial value, and upper bound confidence methods. The results depict that our proposed method significantly performs better than those benchmarking methods in our case test.

Sample efficiency is a crucial problem in Reinforcement Learning, especially when tackling environments with sparse reward signals that make convergence and learning cumbersome. In this work, a novel method is developed that combines Rapidly Exploring Random Trees with Reinforcement Learning to mitigate the inefficiency of the trial-and-error-based experience-gathering concept through the systematic exploration of the state space. The combined approach eliminates the redundancy in irrelevant training samples. Consequently, the pivotal training signals, despite their sparsity, can be further exposed to support the learning process. Experiments are made on several OpenAI gym environments to demonstrate that the proposed method does not have any context-dependent components, and the results show that it can outperform the classic trial-and-error-based training approach.

We examined receptive language developmental trajectories between 18 months and 54 months for three clinical speech-language profile groups of children with cerebral palsy (those with speech motor involvement, without speech motor involvement, and with anarthria) and quantified differences from age-level expectations. We identified latent classes of comprehension development, related these classes to clinical profile groups, and examined how well early receptive language predicted outcomes. We used a prospective longitudinal design. Eighty-five children with cerebral palsy (43 females, 42 males) were followed longitudinally from 18 to 54 months of age. Children were seen two to eight times (322 data points). Children were classified into clinical profile groups. Language comprehension age-equivalent scores were the primary measures of interest. Children with anarthria had significant language delays, limited developmental change over time, and comprised their own latent class. Children with speech motor impairment had slight receptive language delays over time. Children with no speech motor impairment had age-appropriate receptive language over time. Early language comprehension scores were highly predictive of later latent profile group membership. Early language comprehension abilities are highly predictive of language comprehension growth trajectory and suggest that children with early language delay, particularly those who are non-speaking, should receive language intervention to support development. There are two growth trajectories for language comprehension among children with cerebral palsy. Children with speech motor impairment had a constant 6-month receptive language delay. Children without speech motor impairment had age-appropriate receptive language. Non-speaking children had significant receptive language delay. Early language comprehension change was highly predictive of later trajectory group.

Case or agr. Just as abstract Case and agr are cover terms for syntactic features with often idiosyncratic morphological realization, thematic roles seem most useful simply as syntactic designations for positions that enter into argument and adjunct relations. This is a good book, not just for its critique of theta theory, but also for the positive contribution of further development of the Decompositional Theory. Although the book is a revised dissertation, it doesn't read like one: the style is engaging and philosophical, and the exemplification is detailed and clear. And while it does not cover every thematic-role-based proposal ever made, the book is nevertheless to be recommended to anyone who has puzzled over the content of thematic roles. [Edwin Battistella, University of Alabama in Birmingham] Psychology of language: An introduction to sentence and discourse processes. By Murray Singer. Hillsdale, NJ: Lawrence Erlbaum, 1990. Pages xi, 308. $24.95. Recent years have seen the emergence of an essentially interdisciplinary, cognitive-science approach to natural language processing, with some of the most fruitful work focusing on discourse structure and processing. Singer's book is intended as an introductory graduate textbook, though it is also suitable as a desk reference for the linguist, cognitive psychologist, or computer scientist with an interest in natural language processing. An introductory graduate textbook must accomplish several purposes: (i) familiarize students with key theoretical concepts; (ii) refer them to the fundamental literature in which those concepts are discussed; (iii) provide them with exemplars that teach them how to apply the concepts insightfully to the data; and (iv) inculcate a sense of relevance that enables students to read professional articles and evaluate their theoretical significance. S's book is probably above average by these standards. Key concepts are clearly if succinctly explained, fundamental articles are cited in each of the relevant disciplines, and examples are frequent and detailed enough to satisfy the most exacting linguist. The book's weaknesses are those endemic to any introductory text: it emphasizes consensus, spending more time summarizing established results than exploring open issues and controversies, and the passages which explain key concepts are often terse, so that the instructor may sometimes wish to assign source articles as background reading. Overall, the book appears to be a valuable introductory textbook for a course in psycholinguistics or discourse processing. It is divided into ten chapters, as follows: Ch. 1, 'Introduction'; Ch. 2, 'Language and meaning: Representing and remembering discourse'; Ch. 3, 'Syntax and parsing processes'; Ch. 4, The role of knowledge in language comprehension'; Ch. 5, 'Understanding coherent discourse'; Ch. 6, Theme'; Ch. 7, 'Inference processes'; Ch. 8, 'Understanding stories'; Ch. 9, 'Question answering and sentence verification'; and Ch. 10, 'Natural language understanding by computers—and people'. One of the noteworthy aspects of the book is its thorough integration of psycholinguistic data with the concepts of discourse analysis, including coherence, the givennew contract, thematic structure, and scripts. [Paul Deane, University of Central Florida.] An essay on grammar-parser relations. By Jan van de Koot. Dordrecht: Foris, 1990. Pp. xii, 152. Paper $24.50. In this monograph, K investigates the possible relations between grammars and parsers. Any theory of the mind that postulates separate 240 LANGUAGE, VOLUME 68, NUMBER 1 (1992) levels of representations raises the question of what relations are possible, justified and beneficial among the several levels. Two such theories are Marr's theory of vision and Chomskyan generative grammar, with their separation of competence from performance. The book under review belongs to the research line of computer modelling of performance started by Parsifal (Mitchell Marcus, A theory of syntactic recognition for natural language, Cambridge, MA: MIT Press, 1980) in the Government-Binding framework. The monograph starts with a critical introduction to the relevant issues. Through extensive quotations from Marr's work (David Marr, Vision, San Francisco, CA: Freeman, 1982) K presents the methodological justification for multileveled theories of cognition. He then proceeds to explore, in the more limited domain of the language faculty, the necessary features of a psychologically real theory of grammar. The arguments that led some scholars to consider transformational grammar not psychologically real are presented and rebutted by the introduction of a more articulated framework for evaluation, which takes into account the separateness of competence grammar, runtime grammar, parsing technique, and evaluation metrics. Although nothing new is added to the debate here, the main issues of a discussion that spans a decade are reviewed clearly and concisely. Ch. 2 is an overview of several proposals in the framework of deterministic parsing. Most notably, the first such parser, Parsifal, is presented in detail. Arguing against some recent criticism of Parsifal's use of look-ahead, K claims that the use of look-ahead to resolve local ambiguities is empirically correct if coupled with the assumption that lexical-semantic information can be used during syntactic processing, when it is needed for disambiguation. K also reviews the formal properties of Parsifal, drawing on other works in the literature to argue that determinism provides a functional explanation of WH-islands at most, and that it is neutral with respect to grammatical formalism. Ch. 3 explores the relation between the Barriers theory (Noam Chomsky, Barriers. Cambridge, MA: MIT Press, 1986) and deterministic parsing. The parsing platform is Parsifal, with alterations and augmentations that link it more tightly to the grammar and make it more accurate empirically. An algorithm for chain formation is proposed here. K discusses its integration in the existing parser and its application to some linguistic facts, such as violations of the Subject and Adjunct Conditions and parasitic gaps. Some interesting ideas are put forth in this chapter, although more extensive exemplification and, if not a real implementation, at least lower-level specifications of the algorithms would have substantiated the proposal more convincingly. The book ends with a number of theoretical investigations of the possible contribution of the theory of performance to the theory of competence. In general, the reader interested in these issues will find in K's book an accurate and critical review of the main issues in the tradition of deterministic parsing, in itself a needed and useful contribution. Because the book is not intended as a review, however, more space should have been devoted to the author's new proposal; interesting ideas, such as those related to the algorithms for chain formation, are not given enough space and detailed description. The book would have also benefited from more careful editing and typesetting. [Paola Merlo. University ofMaryland.] Politically speaking: The pragmatic analysis of political language. By John Wilson. (Language in Society series.) Basil Blackwell, 1990. Pp. 203. Cloth $45.95, paper $16.95. Politically speaking offers an interesting and frequently amusing look at political speech from the perspective of linguistic pragmatics. Unlike Robin Lakoffs Talking power (New York: Basic Books, 1990), it does not investigate political power or even politics in a generic sense; and, unlike Frederick Bowers's Linguistic aspects oflegislative expression (Vancouver: University of British Columbia Press, 1990). it does not examine statutory language. Rather, Wilson explores politicians' utterances in speeches and interviews. Examples from other cultures are used, but mostly the study deals with recent British and American political figures. A notable feature of the book, W's quotations—from Margaret Thatcher's 'We are a grandmother' to Ronald Reagan's '[in England] a criminal with a gun, even if he was arrested for burglary, was tried for first degree murder and hanged if found

IntroductionTo assess the association between a three-month interruption of language intervention programs and the language performance of children with language delay during the COVID-19 pandemic, and to identify which children are more vulnerable to such interruptions.Materials and methodsThis is a retrospective study involving 33 children with language delay who experienced a three-month suspension of language interventions due to the COVID-19 pandemic. We collected their demographic data and language performance scores from the Comprehensive Developmental Inventory for Infants and Toddlers—Diagnostic test (CDIIT-DT) at four different time points. The scores were analyzed using a Wilcoxon Signed Ranks test.ResultsThe median scores of language comprehension and overall language ability showed a decreasing trend during the interruption period. However, resuming interventions post-interruption showed a statistically significant increase in all language domains. Children in the borderline delay group (CDIIT-DT DQ scores between 71 and 85) were more likely to experience a decline in their language abilities during the interruption.DiscussionThis is the first study to reveal a decreasing trend in language performance during interruption periods, and highlighting the significance of post-interruption language interventions in facilitating improvements. Furthermore, our study brings attention to the heightened vulnerability of children exhibiting borderline language delay in overall language ability tests when faced with interruptions in language interventions.