Related papers: Example-Driven Intent Synthesis for Constrained Da…
The task of information extraction (IE) is to extract structured knowledge from text. However, it is often not straightforward to utilize IE output due to the mismatch between the IE ontology and the downstream application needs. We propose…
While infographics have become a powerful medium for communicating data-driven stories, authoring them from scratch remains challenging, especially for novice users. Retrieving relevant exemplars from a large corpus can provide design…
Aspect-based summarization aims to generate summaries tailored to specific aspects, addressing the resource constraints and limited generalizability of traditional summarization approaches. Recently, large language models have shown promise…
Low-resourced data presents a significant challenge for neural machine translation. In most cases, the low-resourced environment is caused by high costs due to the need for domain experts or the lack of language experts. Therefore,…
The data landscape is rich with structured data, often of high value to organizations, driving important applications in data analysis and machine learning. Recent progress in representation learning and generative models for such data has…
NL2SQL approaches have greatly benefited from the impressive capabilities of large language models (LLMs). In particular, bootstrapping an NL2SQL system for a specific domain can be as simple as instructing an LLM with sufficient contextual…
Industrial recommendation systems are typically composed of multiple stages, including retrieval, ranking, and blending. The retrieval stage plays a critical role in generating a high-recall set of candidate items that covers a wide range…
Traditional database queries follow a simple model: they define constraints that each tuple in the result must satisfy. This model is computationally efficient, as the database system can evaluate the query conditions on each tuple…
Retrieving documents and prepending them in-context at inference time improves performance of language model (LMs) on a wide range of tasks. However, these documents, often spanning hundreds of words, make inference substantially more…
Generative retrieval introduces a groundbreaking paradigm to document retrieval by directly generating the identifier of a pertinent document in response to a specific query. This paradigm has demonstrated considerable benefits and…
This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prompts by removing tokens or lexical units according to their…
This paper presents a novel query clustering approach to capture the broad interest areas of users querying search engines. We make use of recent advances in NLP - word2vec and extend it to get query2vec, vector representations of queries,…
The goal of constraint-based sequence mining is to find sequences of symbols that are included in a large number of input sequences and that satisfy some constraints specified by the user. Many constraints have been proposed in the…
In today's digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to virtual assistants. In these dialogues, it is important to identify user's goals automatically to resolve their…
In this paper, we introduce ReasonEmbed, a novel text embedding model developed for reasoning-intensive document retrieval. Our work includes three key technical contributions. First, we propose ReMixer, a new data synthesis method that…
Product retrieval is the backbone of e-commerce search: for each user query, it identifies a high-recall candidate set from billions of items, laying the foundation for high-quality ranking and user experience. Despite extensive…
We study the problem of set discovery where given a few example tuples of a desired set, we want to find the set in a collection of sets. A challenge is that the example tuples may not uniquely identify a set, and a large number of…
Self-attention based Transformer has demonstrated the state-of-the-art performances in a number of natural language processing tasks. Self-attention is able to model long-term dependencies, but it may suffer from the extraction of…
This paper presents a deployed, production-grade system designed to enhance and scale search query datasets for intent-based recommendation systems in digital banking. In real-world environments, the growing volume and complexity of user…
Database query languages such as SQL for relational databases and Cypher for graph databases have been widely adopted. Recent advancements in large language models (LLMs) enable natural language interactions with databases through models…