Toward Semantics-Based Answer Pinpointing

By Eduard H. Hovy, Laurie Gerber, Ulf Hermjakob, Chin-Yew Lin, Deepak Ravichandran. 2001

297 citations recorded by the source corpus.

We describe the treatment of questions (Question-Answer Typology, question parsing, and results) in the Weblcopedia question answering system.

Subfields: Artificial Intelligence, Question Answering & Reading Comprehension

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

In Question Answering & Reading Comprehension

Citations in the corpus

Finetuned Language Models Are Zero-Shot Learners (2021, neutral): “Question classification: TREC (Li & Roth, 2002; Hovy et al., 2001) 4.”
CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLP (2021, background): “…al. 2018 tab_fact cls/fact checking Chen et al. 2020b trec cls/other Li and Roth 2002; Hovy et al. 2001 trec-finegrained cls/other Li and Roth 2002; Hovy et al. 2001 tweet_eval-emoji cls/emotion Barbieri et al. 2020 tweet_eval-emotion cls/emotion Barbieri et al. 2020 tweet_eval-hate cls/emotion…”
Learning Question Classifiers (2002, background): “Performance of the hierarchical classifier Table 2 shows the P 5 precision of the hierarchical classifier when trained on 5,500 examples and tested on the 500 TREC 10 questions.”
Language Models are General-Purpose Interfaces (2022, background): “• Miscellaneous consists of some additional datasets: CoLA (Warstadt et al., 2019), WiC (Pilehvar and Camacho-Collados, 2019), TREC (Li and Roth, 2002; Hovy et al., 2001).”
Open-domain textual question answering techniques (2003, methodology): “In fact, more and more systems are adopting architectures in which the question semantics are captured prior to retrieving a text paragraph where the answer may lie (Gaizauskas and Humphreys 2000; Hovy, Gerber, Hermjakob, Lin and Ravichandran 2001; Harabagiu, Pas¸ca and Maiorano 2000).”
A survey on question answering technology from an information retrieval perspective (2011, background): “An additional resource is the set of nearly 6,000 labelled questions written in English, which can be used to train question classifiers [152] besides an older collection of questions released by the University of Southern California [51].”
Learning question classifiers: the role of semantic information (2005, background): “2000; Hermjakob 2001; Hovy et al .”
Web-based Question Answering: Revisiting AskMSR (2015, background): “Classifying questions into several pre-defined target answer types has been shown as an important step for locating answer candidates accurately (Hovy et al., 2001; Li and Roth, 2002).”
MMQA: A Multi-domain Multi-lingual Question-Answering Framework for English and Hindi (2018, background): “A dataset11 of 5, 452 questions collected from Hovy et al. (2001), TREC 8 and TREC 9 questions dataset,”
High Accuracy Rule-based Question Classification using Question Syntax and Semantics (2016, background): “While there do exist QA Systems that do not make use of QC, QC has been shown to signiﬁcantly improve the performance of QA systems (Hovy et al., 2001).”