In this paper, we offer a learning framework in which the agent's knowledge gaps are overcome through corrective feedback from a teacher whenever the agent explains its (incorrect) predictions. We test it in a low-resource visual processing scenario, in which the agent must learn to recognize distinct types of toy truck. The agent starts the learning process with no ontology about what types of truck exist nor which parts they have, and a deficient model for recognizing those parts from visual input. The teacher's feedback to the agent's explanations addresses its lack of relevant knowledge in the ontology via a generic rule (e.g., "dump trucks have dumpers"), whereas an inaccurate part recognition is corrected by a deictic statement (e.g., "this is not a dumper"). The learner utilizes this feedback not only to improve its estimate of the hypothesis space of possible domain ontologies and probability distributions over them but also to use those estimates to update its visual interpretation of the scene. Our experiments demonstrate that teacher-learner pairs utilizing explanations and corrections are more data-efficient than those without such a faculty.

We present a procedure for learning to ground symbols from a sequence of stimuli consisting of an arbitrarily complex noun phrase (e.g."all but one green square above both red circles.")and its designation in the visual scene.Our distinctive approach combines: a) lazy fewshot learning to relate open-class words like green and above to their visual percepts; and b) symbolic reasoning with closed-class word categories like quantifiers and negation.We use this combination to estimate new training examples for grounding symbols that occur within a noun phrase but aren't designated by that noun phase (e.g, red in the above example), thereby potentially gaining data efficiency.We evaluate the approach in a visual reference resolution task, in which the learner starts out unaware of concepts that are part of the domain model and how they relate to visual percepts.

Abstract This paper addresses a task in Interactive Task Learning (Laird et al. IEEE Intell Syst 32:6–21, 2017). The agent must learn to build towers which are constrained by rules, and whenever the agent performs an action which violates a rule the teacher provides verbal corrective feedback: e.g. “No, red blocks should be on blue blocks”. The agent must learn to build rule compliant towers from these corrections and the context in which they were given. The agent is not only ignorant of the rules at the start of the learning process, but it also has a deficient domain model, which lacks the concepts in which the rules are expressed. Therefore an agent that takes advantage of the linguistic evidence must learn the denotations of neologisms and adapt its conceptualisation of the planning domain to incorporate those denotations. We show that by incorporating constraints on interpretation that are imposed by discourse coherence into the models for learning (Hobbs in On the coherence and structure of discourse, Stanford University, Stanford, 1985; Asher et al. in Logics of conversation, Cambridge University Press, Cambridge, 2003), an agent which utilizes linguistic evidence outperforms a strong baseline which does not.

Structured models of decision making often assume an agent is aware of all possible states and actions in advance. This assumption is sometimes untenable. In this paper, we learn Bayesian Decision Networks from both domain exploration and expert assertions in a way which guarantees convergence to optimal behaviour, even when the agent starts unaware of actions or belief variables that are critical to success. Our experiments show that our agent learns optimal behaviour on both small and large decision problems, and that allowing an agent to conserve information upon making new discoveries results in faster convergence.

This paper describes a method that predicts which trades players execute during a winlose game.Our method uses data collected from chat negotiations of the game The Settlers of Catan and exploits the conversation to construct dynamically a partial model of each player's preferences.This in turn yields equilibrium trading moves via principles from game theory.We compare our method against four baselines and show that tracking how preferences evolve through the dialogue and reasoning about equilibrium moves are both crucial to success.

Abstract Being able to identify which rhetorical relations (e.g., contrast or explanation) hold between spans of text is important for many natural language processing applications. Using machine learning to obtain a classifier which can distinguish between different relations typically depends on the availability of manually labelled training data, which is very time-consuming to create. However, rhetorical relations are sometimes lexically marked, i.e., signalled by discourse markers (e.g., because, but, consequently etc.), and it has been suggested (Marcu and Echihabi, 2002) that the presence of these cues in some examples can be exploited to label them automatically with the corresponding relation. The discourse markers are then removed and the automatically labelled data are used to train a classifier to determine relations even when no discourse marker is present (based on other linguistic cues such as word co-occurrences). In this paper, we investigate empirically how feasible this approach is. In particular, we test whether automatically labelled, lexically marked examples are really suitable training material for classifiers that are then applied to unmarked examples. Our results suggest that training on this type of data may not be such a good strategy, as models trained in this way do not seem to generalise very well to unmarked data. Furthermore, we found some evidence that this behaviour is largely independent of the classifiers used and seems to lie in the data itself (e.g., marked and unmarked examples may be too dissimilar linguistically and removing unambiguous markers in the automatic labelling process may lead to a meaning shift in the examples).

In this paper we propose a data intensive approach for inferring sentence-internal temporal relations. Temporal inference is relevant for practical NLP applications which either extract or synthesize temporal information (e.g., summarisation, question answering). Our method bypasses the need for manual coding by exploiting the presence of markers like ``after", which overtly signal a temporal relation. We first show that models trained on main and subordinate clauses connected with a temporal marker achieve good performance on a pseudo-disambiguation task simulating temporal inference (during testing the temporal marker is treated as unseen and the models must select the right marker from a set of possible candidates). Secondly, we assess whether the proposed approach holds promise for the semi-automatic creation of temporal annotations. Specifically, we use a model trained on noisy and approximate data (i.e., main and subordinate clauses) to predict intra-sentential relations present in TimeBank, a corpus annotated rich temporal information. Our experiments compare and contrast several probabilistic models differing in their feature space, linguistic assumptions and data requirements. We evaluate performance against gold standard corpora and also against human subjects.

This paper reports on a number of experiments which are designed to investigate the extent to which current NLP resources are able to syntactically and semantically analyse biomedical text. We address two tasks: (a) parsing a real corpus with a hand-built wide-coverage grammar, producing both syntactic analyses and logical forms and (b) automatically computing the interpretation of compound nouns where the head is a nominalisation (e.g. hospital arrival means an arrival at hospital, while patient arrival means an arrival of a patient). For the former task we demonstrate that flexible and yet constrained pre-processing techniques are crucial to success: these enable us to use part-of-speech tags to overcome inadequate lexical coverage, and to package up complex technical expressions prior to parsing so that they are blocked from creating misleading amounts of syntactic complexity. We argue that the XML-processing paradigm is ideally suited for automatically preparing the corpus for parsing. For the latter task, we compute interpretations of the compounds by exploiting surface cues and meaning paraphrases, which in turn are extracted from the parsed corpus. This provides an empirical setting in which we can compare the utility of a comparatively deep parser vs. a shallow one, exploring the trade-off between resolving attachment ambiguities on the one hand and generating errors in the parses on the other. We demonstrate that a model of the meaning of compound nominalisations is achievable with the aid of current broad-coverage parsers.

In this article we investigate logical metonymy, that is, constructions in which the argument of a word in syntax appears to be different from that argument in logical form (e.g., enjoy the book means enjoy reading the book, and easy problem means a problem that is easy to solve). The systematic variation in the interpretation of such constructions suggests a rich and complex theory of composition on the syntax/semantics interface. Linguistic accounts of logical metonymy typically fail to describe exhaustively all the possible interpretations, or they don't rank those interpretations in terms of their likelihood. In view of this, we acquire the meanings of metonymic verbs and adjectives from a large corpus and propose a probabilistic model that provides a ranking on the set of possible interpretations. We identify the interpretations automatically by exploiting the consistent correspondences between surface syntactic cues and meaning. We evaluate our results against paraphrase judgments elicited experimentally from humans and show that the model's ranking of meanings correlates reliably with human intuitions.

We develop a framework for formalizing semantic construction within grammars expressed in typed feature structure logics, including HPSG. The approach provides an alternative to the lambda calculus; it maintains much of the desirable flexibility of unification-based approaches to composition, while constraining the allowable operations in order to capture basic generalizations and improve maintainability.

We describe the use of XML tokenisation, tagging and mark-up tools to prepare a corpus for parsing. Our techniques are generally applicable but here we focus on parsing Medline abstracts with the ANLT wide-coverage grammar. Hand-crafted grammars inevitably lack coverage but many coverage failures are due to inadequacies of their lexicons. We describe a method of gaining a degree of robustness by interfacing POS tag information with the existing lexicon. We also show that XML tools provide a sophisticated approach to pre-processing, helping to ameliorate the 'messiness' in real language data and improve parse performance.

We describe a formal framework for interpretation of words and compounds in a discourse context which integrates a symbolic lexicon/grammar, word-sense probabilities, and a pragmatic component. The approach is motivated by the need to handle productive word use. In this paper, we concentrate on compound nominals. We discuss the inadequacies of approaches which consider compund interpretation as either wholly lexico-grammatical or wholly pragmatic, and provide an alternative integrated account.

This paper is about the flow of inference between communicative intentions, discourse structure and the domain during discourse processing. We augment a theory of discourse interpretation with a theory of distinct mental attitudes and reasoning about them, in order to provide an account of how the attitudes interact with reasoning about discourse structure.

We investigate various contextual effects on text interpretation, and account for them by providing contextual constraints in a logical theory of text interpretation. On the basis of the way these constraints interact with the other knowledge sources, we draw some general conclusions about the role of domain-specific information, top-down and bottom-up discourse information flow, and the usefulness of formalisation in discourse theory.

This paper presents a formal account of the temporal interpretation of text. The distinct natural interpretations of texts with similar syntax are explained in terms of defeasible rules characterising causal laws and Gricean-style pragmatic maxims. Intuitively compelling patterns of defeasible entailment that are supported by the logic in which the theory is expressed are shown to underly temporal interpretation.