Identifying linguistic knowledge for textual inference
نویسنده
چکیده
The ability to recognize whether one text can be inferred from another is a critical element of various computational linguistics tasks. The current work explores what kind of linguistic information is useful, or even necessary, in making such inference judgments and how well an inference model using minimal representation and linguistic information performs on an inference judgment task.
منابع مشابه
Construction of a Simple Inference System of Textural Similarity (oka1 RITE2)
The motivation to join the RITE-2 task is to understand what kinds of linguistic and common knowledge are needed to recognize textual similarity in RITE-2 data. After a shallow manual analysis of RITE-2-bc example data, we found that morpheme similarity would be a major factor to recognize textual similarity. Thus we construct a threshold based inference system with Japanese WordNet as a base s...
متن کاملTextual Enhancement across Linguistic Structures: EFL Learners' Acquisition of English Forms
The benefits of textual input enhancement in the acquisition of linguistic forms have produced mixed results in SLA literature. The present study investigates the effects of textual enhancement on adult foreign language intake of two English linguistic forms-subjunctive mood and inversion structures-to explore the role of the type of linguistic items in input enhancement studies. It also invest...
متن کاملParis: a Parallel Inference System 1
This paper presents an inferential system based on abductive interpretation of text. Inference to the best explanation is performed by the recognition of the most economic semantic paths produced by the propagation of markers on a very large linguistic knowledge base. The propagation of markers is controlled by their intrinsic propagation rules, devised from plausible semantic relation chains. ...
متن کاملEntailment Rules for Predicates: Representation, Learning, Application and Evaluation
A fundamental phenomenon in natural languages is the ability to infer a specific meaning from different textual expressions. Correspondingly, within many NLP applications it is vital to identify the various ways in which a target meaning might be conveyed. For example, NLP systems should be able to infer that “Tom Cruise is married” from the text “Katie Holmes wants to divorce Tom Cruise”. To p...
متن کاملBuilding Textual Entailment Specialized Data Sets: a Methodology for Isolating Linguistic Phenomena Relevant to Inference
This paper proposes a methodology for the creation of specialized data sets for Textual Entailment, made of monothematic Text-Hypothesis pairs (i.e. pairs in which only one linguistic phenomenon relevant to the entailment relation is highlighted and isolated). The annotation procedure assumes that humans have knowledge about the linguistic phenomena relevant to inference, and a classification o...
متن کامل