No abstract

Fact-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. This poses a huge challenge to question answering (QA) systems that typically rely on cues in full-fledged interrogative sentences. As a solution, we develop Convex: an unsupervised method that can answer incomplete questions over a knowledge graph (KG) by maintaining conversation context using entities and predicates seen so far and automatically inferring missing or ambiguous pieces for follow-up questions. The core of our method is a graph exploration algorithm that judiciously expands a frontier to find candidate answers for the current question. To evaluate Convex, we release ConvQuestions, a crowdsourced benchmark with 11, 200 distinct conversations from five different domains. We show that Convex: (i) adds conversational support to any stand-alone QA system, and (ii) outperforms state-of-the-art baselines and question completion strategies.

We propose FINET, a system for detecting the types of named entities in short inputs-such as sentences or tweets-with respect to WordNet's super fine-grained type system. FINET generates candidate types using a sequence of multiple extractors, ranging from explicitly mentioned types to implicit types, and subsequently selects the most appropriate using ideas from word-sense disambiguation. FINET combats data scarcity and noise from existing systems: It does not rely on supervision in its extractors and generates training data for type selection from WordNet and other resources. FINET supports the most fine-grained type system so far, including types with no annotated training data. Our experiments indicate that FINET outperforms state-of-the-art methods in terms of recall, precision, and granularity of extracted types.

No abstract

Direct answering of questions that involve multiple entities and relations is a challenge for text-based QA. This problem is most pronounced when answers can be found only by joining evidence from multiple documents. Curated knowledge graphs (KGs) may yield good answers, but are limited by their inherent incompleteness and potential staleness. This paper presents QUEST, a method that can answer complex questions directly from textual sources on-the-fly, by computing similarity joins over partial results from different documents. Our method is completely unsupervised, avoiding trainingdata bottlenecks and being able to cope with rapidly evolving ad hoc topics and formulation style in user questions. QUEST builds a noisy quasi KG with node and edge weights, consisting of dynamically retrieved entity names and relational phrases. It augments this graph with types and semantic alignments, and computes the best answers by an algorithm for Group Steiner Trees. We evaluate QUEST on benchmarks of complex questions, and show that it substantially outperforms state-of-the-art baselines.

We present QUINT, a live system for question answering over knowledge bases. QUINT automatically learns role-aligned utterance-query templates from user questions paired with their answers. When QUINT answers a question, it visualizes the complete derivation sequence from the natural language utterance to the final answer. The derivation provides an explanation of how the syntactic structure of the question was used to derive the structure of a SPARQL query, and how the phrases in the question were used to instantiate different parts of the query. When an answer seems unsatisfactory, the derivation provides valuable insights towards reformulating the question.

Answering complex questions is one of the challenges that questionanswering (QA) systems face today. While complexity has several facets, question dimensions like temporal and spatial intents necessitate specialized treatment. Methods geared towards such questions need benchmarks that reflect the desired aspects and challenges. Here, we take a key step in this direction, and release a new benchmark, TempQuestions, containing 1, 271 questions, that are all temporal in nature, paired with their answers. As a key contribution that enabled the creation of this resource, we provide a crisp definition for temporal questions. Most questions require decomposing them into sub-questions, and the questions are of a kind that they would be best evaluated on a combination of structured data and unstructured text sources. Experiments with two QA systems demonstrate the need for further research on complex questions.

Today's openly available knowledge bases, such as DBpedia, Yago, Wikidata or Freebase, capture billions of facts about the world's entities. However, even the largest among these (i) are still limited in up-to-date coverage of what happens in the real world, and (ii) miss out on many relevant predicates that precisely capture the wide variety of relationships among entities. To overcome both of these limitations, we propose a novel approach to build on-the-fly knowledge bases in a query-driven manner. Our system, called QKBfly, supports analysts and journalists as well as question answering on emerging topics, by dynamically acquiring relevant facts as timely and comprehensively as possible. QKBfly is based on a semantic-graph representation of sentences, by which we perform three key IE tasks, namely named-entity disambiguation, co-reference resolution and relation extraction, in a light-weight and integrated manner. In contrast to Open IE, our output is canonicalized. In contrast to traditional IE, we capture more predicates, including ternary and higher-arity ones. Our experiments demonstrate that QKBfly can build high-quality, on-the-fly knowledge bases that can readily be deployed, e.g., for the task of ad-hoc question answering. PVLDB Reference Format: