Abductive Reasoning with a Large Knowledge Base for Discourse Processing (original) (raw)
Related papers
Approaching textual entailment with LFG and FrameNet frames
Proc. of the Second PASCAL RTE Challenge …, 2006
We present a baseline system for modeling textual entailment that combines deep syntactic analysis with structured lexical meaning descriptions in the FrameNet paradigm. Textual entailment is approximated by degrees of structural and semantic overlap of text and hypothesis, which we measure in a match graph. The encoded measures of similarity are processed in a machine learning setting. 1
A Discourse Commitment-Based Framework for Recognizing Textual Entailment
In this paper, we introduce a new framework for recognizing textual entailment which de- pends on extraction of the set of publicly- held beliefs - known as discourse commit- ments - that can be ascribed to the author of a text or a hypothesis. Once a set of commit- ments have been extracted from a t-h pair, the task of recognizing textual entailment is reduced to the identification of the commit- ments from a t which support the inference of the h. Promising results were achieved: our system correctly identified more than 80% of examples from the RTE-3 Test Set correctly, without the need for additional sources of training data or other web-based resources.
Recognising entailment within discourse
Proceedings of the 23rd …, 2010
Texts are commonly interpreted based on the entire discourse in which they are situated. Discourse processing has been shown useful for inference-based application; yet, most systems for textual entailment -a generic paradigm for applied inference -have only addressed discourse considerations via off-the-shelf coreference resolvers. In this paper we explore various discourse aspects in entailment inference, suggest initial solutions for them and investigate their impact on entailment performance. Our experiments suggest that discourse provides useful information, which significantly improves entailment inference, and should be better addressed by future entailment systems.
A Knowledge-Based Textual Entailment Approach Applied to the AVE Task
Lecture Notes in Computer Science, 2007
The Answer Validation Exercise (AVE) is a pilot track within the Cross-Language Evaluation Forum (CLEF) 2006. The AVE competition provides an evaluation framework for answer validations in Question Answering (QA). In our participation in AVE, we propose a system that has been initially used for other task as Recognising Textual Entailment (RTE). The aim of our participation is to evaluate the improvement our system brings to QA. Moreover, due to the fact that these two task (AVE and RTE) have the same main idea, which is to find semantic implications between two fragments of text, our system has been able to be directly applied to the AVE competition. Our system is based on the representation of the texts by means of logic forms and the computation of semantic comparison between them. This comparison is carried out using two different approaches. The first one managed by a deeper study of the Word-Net relations, and the second uses the measure defined by Lin in order to compute the semantic similarity between the logic form predicates. Moreover, we have also designed a voting strategy between our system and the MLEnt system, also presented by the University of Alicante, with the aim of obtaining a joint execution of the two systems developed at the University of Alicante. Although the results obtained have not been very high, we consider that they are quite promising and this supports the fact that there is still a lot of work on researching in any kind of textual entailment.
Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference
Natural Language Inference (NLI), also known as Recognizing Textual Entailment (RTE), is one of the most important problems in natural language processing. It requires to infer the logical relationship between two given sentences. While current approaches mostly focus on the interaction architectures of the sentences, in this paper, we propose to transfer knowledge from some important discourse markers to augment the quality of the NLI model. We observe that people usually use some discourse markers such as "so" or "but" to represent the logical relationship between two sentences. These words potentially have deep connections with the meanings of the sentences, thus can be utilized to help improve the representations of them. Moreover, we use reinforcement learning to optimize a new objective function with a reward defined by the property of the NLI datasets to make full use of the labels information. Experiments show that our method achieves the state-of-the-art performance on several large-scale datasets. 1 Here sentences mean either the whole sentences or the main clauses of a compound sentence.
From Lexical Entailment to Recognizing Textual Entailment Using Linguistic Resources
2009
In this paper, we introduce our Recognizing Textual Entailment (RTE) system developed on the basis of Lexical Entailment between two text excerpts, namely the hypothesis and the text. To extract atomic parts of hypotheses and texts, we carry out syntactic parsing on the sentences. We then utilize WordNet and FrameNet lexical resources for estimating lexical coverage of the text on the hypothesis. We report the results of our RTE runs on the Text Analysis Conference RTE datasets. Using a failure analysis process, we also show that the main difficulty of our RTE system relates to the underlying difficulty of syntactic analysis of sentences.
Generating Entailment Rules from FrameNet
2010
Many NLP tasks need accurate knowledge for semantic inference. To this end, mostly WordNet is utilized. Yet Word-Net is limited, especially for inference between predicates. To help filling this gap, we present an algorithm that generates inference rules between predicates from FrameNet. Our experiment shows that the novel resource is effective and complements WordNet in terms of rule coverage.
A semantic approach to textual entailment: System evaluation and task analysis
Proceedings of the ACL- …, 2007
Recognizing and generating textual entailment and paraphrases are regarded as important technologies in a broad range of NLP applications, including, information extraction, summarization, question answering, information retrieval, machine translation and text generation. Both textual entailment and paraphrasing address relevant aspects of natural language semantics. Entailment is a directional relation between two expressions in which one of them implies the other, whereas paraphrase is a relation in which two expressions convey essentially the same meaning. Indeed, paraphrase can be defined as bi-directional entailment. While it may be debatable how such semantic definitions can be made well-founded, in practice we have already seen evidence that such knowledge is essential for many applications.
Design and realization of a modular architecture for textual entailment
2013
A key challenge at the core of many NLP tasks is the ability to determine which conclusions can be inferred from a given natural language text. This problem, called the Recognition of Textual Entailment (RTE), has initiated the development of a range of algorithms, methods and technologies. Unfortunately, research on TE (like semantics research more generally), is fragmented into studies focussing on various aspects of semantics such as world knowledge, lexical and syntactic relations, or more specialized kinds of inference. This fragmentation has problematic practical consequences. Notably, interoperability among existing RTE systems is poor, and reuse of resources and algorithms is mostly infeasible. This also makes systematic evaluations very difficult to carry out. Finally, TE presents a wide array of approaches to potential end users with little guidance on which to pick. Our contribution to this situation is the novel EXCITEMENT architecture, which was developed to enable and encourage the consolidation of methods and resources in the TE area. It decomposes RTE into components with strongly typed interfaces. We specify (a) a modular linguistic analysis pipeline and (b) a decomposition of the "core" RTE methods
… , mobile Kommunikation und …, 2005
In this paper, we present a rule-based system for the assignment of FrameNet frames by way of a "detour via WordNet". The system can be used to overcome sparse-data problems of statistical systems trained on current FrameNet data. We devise a weighting scheme to select the best frame(s) out of a set of candidate frames, and present first figures of evaluation.