Natural language question answering: the view from here

By Lynette Hirschman, Robert J. Gaizauskas. Natural Language Engineering, 2001

534 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4fcc00570dcf797c3f18fbc5df926edd79ffb3b3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Natural Language Questions for the Web of Data (2012, methodology): “State-of-the-art methods (Hirschman and Gaizauskas, 2001; Kwok et al., 2001; Zheng, 2002; Katz et al., 2007; Dang et al., 2007; Voorhees, 2003) cast the user’s question into a keyword query to a Web search engine (perhaps with phrases for location and person names or other proper nouns).”
A survey on question answering technology from an information retrieval perspective (2011, background): “The author reports that 36.4% of errors in question answering on TREC-8, 9 and 10 data are caused by incorrect EAT estimation.”
Question classification with log-linear models (2006, background): “The most common approach to semantic interpretation is to classify the question into a closed set of question classes or question types (qtype) which describe the expected semantic category of the answer to the question [ 11 ].”
An Empirical Analysis of NMT-Derived Interlingual Embeddings and Their Use in Parallel Sentence Identification (2017, background): “Efforts have been carried out to approach cross-language versions of these tasks without translating all the texts into one common language (e.g., (Bouma et al., 2008; Mu˜noz Terol et al., 2008; Potthast et al., 2011)), but using inter-lingua or multilingual representations instead.”
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization (2023, background): “Large language models (LLMs) have attracted increasing attention in the field of artificial intelligence [1, 2, 3, 4, 5, 6], with various applications from question answering [7, 8], machine translation [9, 10] to content creation [11, 12].”
Retrieve-and-Read: Multi-task Learning of Information Retrieval and Reading Comprehension (2018, methodology): “sttraditionalsystemsfocus on factoid questions, which can be answered with named entities, andhaveapipelinearchitectureconsistingofatleastthreecomponents: question analysis, IR, and answer extraction [17]. The systems reformulate queries toenable their IR method to cover many textualvariants.However”
Enabling deep learning for large scale question answering in Italian (2019, unknown): “Question Answering (QA) ([8]) tackles the problem of returning one or more answers to a question posed by a user in natural language, using as source a large knowledge base or, even more often, a large scale text collection: in this setting, the answers correspond to sentences (or their fragments)…”
Answering Clinical Questions with Knowledge-Based and Statistical Techniques (2007, background): “This classiﬁer also outputs the probability of a class assignment.”
Toponym resolution in text: annotation, evaluation and applications of spatial grounding (2007, methodology): “But a crucial development was SRI’s move for MUC-4 from TACITUS (Hobbs (1986)), a ‘deep’ text understanding system based on syntactic analysis and abductive inference, to FASTUS (Hobbs (1992); Appelt et al.”
Quantitative evaluation of passage retrieval algorithms for question answering (2003, background): “Categories and Subject Descriptors H.3.4 [Information Systems]: Information Storage and Retrieval, Systems and Software General Terms Measurement, performance, standardization, design Keywords Question answering, passage retrieval”
Applications of Topic Models (2017, background): “The poor user—faced with documents that would take a decade to read—is looking for a single needle: a document (or at most a handful of documents) that matches what the user is looking for: a “smoking gun” e-mail, the document that best represents a concept [Salton, 1968] or the answer to a question”