Question Answering using Sentence Parsing and Semantic Network Matching

نویسنده

  • Sven Hartrumpf
چکیده

The paper describes a question answering system for German called InSicht. All documents in the system are analyzed by a syntactico-semantic parser in order to represent each document sentence by a semantic network (in the MultiNet formalism) or a partial semantic network (if only a parse in chunk mode succeeds). A question sent to InSicht is parsed yielding its semantic network representation and its sentence type. The semantic network is expanded to equivalent or similar semantic networks (query expansion stage) by applying equivalence rules, implicational rules (in backward chaining), and concept variations based on semantic relations in computer lexicons and other knowledge sources. During the search stage, every semantic network generated for the question is matched with semantic networks for document sentences. For efficiency, a concept index server is applied to reduce the number of matches tried. If a match succeeds, an answer string is generated from the matching semantic network in the supporting document by answer generation rules. Among competing answers, one answer is chosen by combining a preference for longer answers and a preference for more frequent answers. The system is evaluated on the QA@CLEF 2004 test set. A hierarchy of problem classes is proposed and a sample of suboptimally answered questions is annotated with problem classes from this hierarchy. Finally, some conclusions are drawn, main problems are identified, and directions for future work as suggested by these problems are indicated.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Convolutional Neural Tensor Network Architecture for Community-Based Question Answering

Retrieving similar questions is very important in community-based question answering. A major challenge is the lexical gap in sentence matching. In this paper, we propose a convolutional neural tensor network architecture to encode the sentences in semantic space and model their interactions with a tensor layer. Our model integrates sentence modeling and semantic matching into a single model, w...

متن کامل

Question-Answering Using Semantic Relation Triples

This paper describes the development of a prototype system to answer questions by selecting sentences from the documents in which the answers occur. After parsing each sentence in these documents, databases are constructed by extracting relational triples from the parse output. The triples consist of discourse entities, semantic relations, and the governing words to which the entities are bound...

متن کامل

Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

We propose a novel semantic parsing framework for question answering using a knowledge base. We define a query graph that resembles subgraphs of the knowledge base and can be directly mapped to a logical form. Semantic parsing is reduced to query graph generation, formulated as a staged search problem. Unlike traditional approaches, our method leverages the knowledge base in an early stage to p...

متن کامل

Question Answering Using Enhanced Lexical Semantic Models

In this paper, we study the answer sentence selection problem for question answering. Unlike previous work, which primarily leverages syntactic analysis through dependency tree matching, we focus on improving the performance using models of lexical semantic resources. Experiments show that our systems can be consistently and significantly improved with rich lexical semantic information, regardl...

متن کامل

برچسب‌زنی خودکار نقش‌های معنایی در جملات فارسی به کمک درخت‌های وابستگی

Automatic identification of words with semantic roles (such as Agent, Patient, Source, etc.) in sentences and attaching correct semantic roles to them, may lead to improvement in many natural language processing tasks including information extraction, question answering, text summarization and machine translation. Semantic role labeling systems usually take advantage of syntactic parsing and th...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2004