Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMay 2024
TIQ: A Benchmark for Temporal Question Answering with Implicit Time Constraints
WWW '24: Companion Proceedings of the ACM Web Conference 2024Pages 1394–1399https://doi.org/10.1145/3589335.3651895Temporal question answering (QA) involves explicit (e.g., "...before 2024") or implicit (e.g., "...during the Cold War period") time constraints. Implicit constraints are more challenging; yet benchmarks for temporal QA largely disregard such questions. ...
- short-paperMay 2024
CompMix: A Benchmark for Heterogeneous Question Answering
WWW '24: Companion Proceedings of the ACM Web Conference 2024Pages 1091–1094https://doi.org/10.1145/3589335.3651444Fact-centric question answering (QA) often requires access to multiple, heterogeneous, information sources. By jointly considering several sources like a knowledge base (KB), a text collection, and tables from the web, QA systems can enhance their answer ...
Faithful Temporal Question Answering over Heterogeneous Sources
WWW '24: Proceedings of the ACM Web Conference 2024Pages 2052–2063https://doi.org/10.1145/3589334.3645547Temporal question answering (QA) involves time constraints, with phrases such as "... in 2019" or "... before COVID". In the former, time is an explicit condition, in the latter it is implicit. State-of-the-art methods have limitations along three ...
- research-articleMarch 2024
Robust Training for Conversational Question Answering Models with Reinforced Reformulation Generation
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 322–331https://doi.org/10.1145/3616855.3635822Models for conversational question answering (ConvQA) over knowledge graphs (KGs) are usually trained and tested on benchmarks of gold QA pairs. This implies that training is limited to surface forms seen in the respective datasets, and evaluation is on ...
- research-articleJuly 2023
Explainable Conversational Question Answering over Heterogeneous Sources via Iterative Graph Neural Networks
SIGIR '23: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information RetrievalPages 643–653https://doi.org/10.1145/3539618.3591682In conversational question answering, users express their information needs through a series of utterances with incomplete context. Typical ConvQA methods rely on a single source (a knowledge base (KB), or a text corpus, or a set of tables), thus being ...
- short-paperFebruary 2023
CoQEx: Entity Counts Explained
WSDM '23: Proceedings of the Sixteenth ACM International Conference on Web Search and Data MiningPages 1168–1171https://doi.org/10.1145/3539597.3573021For open-domain question answering, queries on entity counts, such ashow many languages are spoken in Indonesia, are challenging. Such queries can be answered through succinct contexts with counts:estimated 700 languages, and instances:Javanese and ...
- short-paperJuly 2022
Answering Count Queries with Explanatory Evidence
SIGIR '22: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information RetrievalPages 2415–2419https://doi.org/10.1145/3477495.3531870A challenging case in web search and question answering are count queries, such as"number of songs by John Lennon''. Prior methods merely answer these with a single, and sometimes puzzling number or return a ranked list of text snippets with different ...
- research-articleJuly 2022
Conversational Question Answering on Heterogeneous Sources
SIGIR '22: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information RetrievalPages 144–154https://doi.org/10.1145/3477495.3531815Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a knowledge base (KB), or a text ...
- research-articleFebruary 2022
Beyond NED: Fast and Effective Search Space Reduction for Complex Question Answering over Knowledge Bases
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data MiningPages 172–180https://doi.org/10.1145/3488560.3498488Answering complex questions over knowledge bases (KB-QA) faces huge input data with billions of facts, involving millions of entities and thousands of predicates. For efficiency, QA systems first reduce the answer search space by identifying a set of ...
- research-articleJuly 2021
Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs
SIGIR '21: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information RetrievalPages 459–469https://doi.org/10.1145/3404835.3462859The rise of personal assistants has made conversational question answering (ConvQA) a very popular mechanism for user-system interaction. State-of-the-art methods for ConvQA over knowledge graphs (KGs) can only learn from crisp question-answer pairs ...
- research-articleJuly 2020
Conversational Question Answering over Passages by Leveraging Word Proximity Networks
SIGIR '20: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information RetrievalPages 2129–2132https://doi.org/10.1145/3397271.3401399Question answering (QA) over text passages is a problem of longstanding interest in information retrieval. Recently, the conversational setting has attracted attention, where a user asks a sequence of questions to satisfy her information needs around a ...
- research-articleJanuary 2020
Entities with Quantities: Extraction, Search, and Ranking
WSDM '20: Proceedings of the 13th International Conference on Web Search and Data MiningPages 833–836https://doi.org/10.1145/3336191.3371860Quantities are more than numeric values. They represent measures for entities, expressed in numbers with associated units. Search queries often include quantities, such as athletes who ran 200m under 20 seconds or companies with quarterly revenue above $...
- research-articleNovember 2019
Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion
CIKM '19: Proceedings of the 28th ACM International Conference on Information and Knowledge ManagementPages 729–738https://doi.org/10.1145/3357384.3358016Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic. In such a conversational setting, the user's inputs are often incomplete, with entities or predicates left out, and ungrammatical phrases. ...
- short-paperOctober 2018
TEQUILA: Temporal Question Answering over Knowledge Bases
CIKM '18: Proceedings of the 27th ACM International Conference on Information and Knowledge ManagementPages 1807–1810https://doi.org/10.1145/3269206.3269247Question answering over knowledge bases (KB-QA) poses challenges in handling complex questions that need to be decomposed into sub-questions. An important case, addressed here, is that of temporal questions, where cues for temporal relations need to be ...
- research-articleApril 2018
TempQuestions: A Benchmark for Temporal Question Answering
WWW '18: Companion Proceedings of the The Web Conference 2018Pages 1057–1062https://doi.org/10.1145/3184558.3191536Answering complex questions is one of the challenges that question-answering (QA) systems face today. While complexity has several facets, question dimensions like temporal and spatial intents necessitate specialized treatment. Methods geared towards ...
- research-articleApril 2018
Never-Ending Learning for Open-Domain Question Answering over Knowledge Bases
WWW '18: Proceedings of the 2018 World Wide Web ConferencePages 1053–1062https://doi.org/10.1145/3178876.3186004Translating natural language questions to semantic representations such as SPARQL is a core challenge in open-domain question answering over knowledge bases (KB-QA). Existing methods rely on a clear separation between an offline training phase, where a ...
- research-articleApril 2017
Automated Template Generation for Question Answering over Knowledge Graphs
WWW '17: Proceedings of the 26th International Conference on World Wide WebPages 1191–1200https://doi.org/10.1145/3038912.3052583Templates are an important asset for question answering over knowledge graphs, simplifying the semantic parsing of input utterances and generating structured queries for interpretable answers. State-of-the-art methods rely on hand-crafted templates with ...
- research-articleOctober 2013
Robust question answering over the web of linked data
CIKM '13: Proceedings of the 22nd ACM international conference on Information & Knowledge ManagementPages 1107–1116https://doi.org/10.1145/2505515.2505677Knowledge bases and the Web of Linked Data have become important assets for search, recommendation, and analytics. Natural-language questions are a user-friendly mode of tapping this wealth of knowledge and data. However, question answering technology ...
- ArticleSeptember 2011
YAGO-QA: Answering Questions by Structured Knowledge Queries
ICSC '11: Proceedings of the 2011 IEEE Fifth International Conference on Semantic ComputingPages 158–161https://doi.org/10.1109/ICSC.2011.30We present a natural-language question-answering system that gives access to the accumulated knowledge of one of the largest community projects on the Web â " Wikipedia â " via an automatically acquired structured knowledge base. Key to building such a ...