Related papers: A Concise Query Language with Search and Transform…
Argumentation mining (AM) requires the identification of complex discourse structures and has lately been applied with success monolingually. In this work, we show that the existing resources are, however, not adequate for assessing…
Most previous work on the recently developed language-modeling approach to information retrieval focuses on document-specific characteristics, and therefore does not take into account the structure of the surrounding corpus. We propose a…
Multi-model databases are designed to store, manage, and query data in various models, such as relational, hierarchical, and graph data, simultaneously. In this paper, we provide a theoretical basis for querying categorical databases. We…
Users issue queries to Search Engines, and try to find the desired information in the results produced. They repeat this process if their information need is not met at the first place. It is crucial to identify the important words in a…
Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic…
We present a universal framework to model contextualized sentence representations with visual awareness that is motivated to overcome the shortcomings of the multimodal parallel data with manual annotations. For each sentence, we first…
Multilinguality is gradually becoming ubiquitous in the sense that more and more researchers have successfully shown that using additional languages help improve the results in many Natural Language Processing tasks. Multilingual Multiway…
We consider strategies to organize easily updatable associative arrays in external memory. These arrays are used for full-text search. We study indexes with different keys: single word form, two word forms, and sequences of word forms. The…
Regular path query languages for data graphs are essentially \emph{untyped}. The lack of type information greatly limits the optimization opportunities for query engines and makes application development more complex. In this paper we…
Intention identification is a core issue in dialog management. However, due to the non-canonicality of the spoken language, it is difficult to extract the content automatically from the conversation-style utterances. This is much more…
We report on a language resource consisting of 2000 annotated bibliography entries, which is being analyzed as part of our research on indicative document summarization. We show how annotated bibliographies cover certain aspects of…
Increased adaptability of RNN language models leads to improved predictions that benefit many applications. However, current methods do not take full advantage of the RNN structure. We show that the most widely-used approach to adaptation…
We introduce Ideograph, a language for expressing and manipulating structured data. Its types describe kinds of structures, such as natural numbers, lists, multisets, binary trees, syntax trees with variable binding, directed multigraphs,…
When used in high-stakes settings, AI systems are expected to produce decisions that are transparent, interpretable and auditable, a requirement increasingly expected by regulations. Decision trees such as CART provide clear and verifiable…
Neural architecture search methods are able to find high performance deep learning architectures with minimal effort from an expert. However, current systems focus on specific use-cases (e.g. convolutional image classifiers and recurrent…
Users try to articulate their complex information needs during search sessions by reformulating their queries. To make this process more effective, search engines provide related queries to help users in specifying the information need in…
The challenge of answering graph queries over incomplete knowledge graphs is gaining significant attention in the machine learning community. Neuro-symbolic models have emerged as a promising approach, combining good performance with high…
The schema.org initiative led by the four major search engines curates a vocabulary for describing web content. The number of semantic annotations on the web are increasing, mostly due to the industrial incentives provided by those search…
We present Broccoli, a fast and easy-to-use search engine for what we call semantic full-text search. Semantic full-text search combines the capabilities of standard full-text search and ontology search. The search operates on four kinds of…
We introduce STREET, a unified multi-task and multi-domain natural language reasoning and explanation benchmark. Unlike most existing question-answering (QA) datasets, we expect models to not only answer questions, but also produce…