Search Results for author:
Found 33 papers, 17 papers with code
Interview: Large-scale Modeling of Media Dialog with Discourse Patterns and Knowledge Grounding
In this work, we perform the first large-scale analysis of discourse in media dialog and its impact on generative modeling of dialog turns, with a focus on interrogative patterns and use of external knowledge.
Multi-stage Training with Improved Negative Contrast for Neural Passage Retrieval
In the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion.
Leveraging LLMs for Synthesizing Training Data Across Many Languages in Multilingual Dense Retrieval
There has been limited success for dense retrieval models in multilingual retrieval, due to uneven and scarce training data available across multiple languages.
Farzi Data: Autoregressive Data Distillation
We study data distillation for auto-regressive machine learning tasks, where the input and output have a strict left-to-right causal structure.
Do LLMs Understand User Preferences? Evaluating LLMs On User Rating Prediction
In this paper, we conduct a thorough examination of both CF and LLMs within the classic task of user rating prediction, which involves predicting a user's rating for a candidate item based on their past ratings.
WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset
Webpages have been a rich resource for language and vision-language tasks.
A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding
Webpages have been a rich, scalable resource for vision-language and language only tasks.
HYRR: Hybrid Infused Reranking for Passage Retrieval
We present Hybrid Infused Reranking for Passages Retrieval (HYRR), a framework for training rerankers based on a hybrid of BM25 and neural retrieval models.
RISE: Leveraging Retrieval Techniques for Summarization Evaluation
RISE is first trained as a retrieval task using a dual-encoder retrieval setup, and can then be subsequently utilized for evaluating a generated summary given an input document, without gold reference summaries.
Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models
We take human annotations as a gold standard and show that a correlated automatic metric is suitable for development.
RankT5: Fine-Tuning T5 for Text Ranking with Ranking Losses
Recently, substantial progress has been made in text ranking based on pretrained language models such as BERT.
Knowledge Prompts: Injecting World Knowledge into Language Models through Soft Prompts
The resulting soft knowledge prompts (KPs) are task independent and work as an external memory of the LMs.
Promptagator: Few-shot Dense Retrieval From 8 Examples
To amplify the power of a few examples, we propose Prompt-base Query Generation for Retriever (Promptagator), which leverages large language models (LLM) as a few-shot query generator, and creates task-specific retrievers based on the generated data.
Knowledge-aware Neural Collective Matrix Factorization for Cross-domain Recommendation
In this paper, we propose to incorporate the knowledge graph (KG) for CDR, which enables items in different domains to share knowledge.
Exploring Dual Encoder Architectures for Question Answering
We further explore and explain why parameter sharing in projection layer significantly improves the efficacy of the dual encoders, by directly probing the embedding spaces of the two encoder towers with t-SNE algorithm.
Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$
Recent neural network-based language models have benefited greatly from scaling up the size of training datasets and the number of parameters in the models themselves.
Transformer Memory as a Differentiable Search Index
In this paper, we demonstrate that information retrieval can be accomplished with a single Transformer, in which all information about the corpus is encoded in the parameters of the model.
Large Dual Encoders Are Generalizable Retrievers
With multi-stage training, surprisingly, scaling up the model size brings significant improvement on a variety of retrieval tasks, especially for out-of-domain generalization.
Ranked #9 on
Zero-shot Text Search
on BEIR
LongT5: Efficient Text-To-Text Transformer for Long Sequences
Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models.
Ranked #1 on
Text Summarization
on BigPatent
ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning
Despite the recent success of multi-task learning and transfer learning for natural language processing (NLP), few works have systematically studied the effect of scaling up the number of tasks during pre-training.
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models
To support our investigation, we establish a new sentence representation transfer benchmark, SentGLUE, which extends the SentEval toolkit to nine tasks from the GLUE benchmark.
SHARE: a System for Hierarchical Assistive Recipe Editing
The large population of home cooks with dietary restrictions is under-served by existing cooking resources and recipe generation models.
Neural Passage Retrieval with Improved Negative Contrast
In this paper we explore the effects of negative sampling in dual encoder models used to retrieve passages for automatic question answering.
Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays
In this work, we focus on reporting abnormal findings on radiology images; instead of training on complete radiology reports, we propose a method to identify abnormal findings from the reports in addition to grouping them with unsupervised clustering and minimal rules.
Interview: A Large-Scale Open-Source Corpus of Media Dialog
Compared to existing large-scale proxies for conversational data, language models trained on our dataset exhibit better zero-shot out-of-domain performance on existing spoken dialog datasets, demonstrating its usefulness in modeling real-world conversations.
Addressing Marketing Bias in Product Recommendations
However, these interactions can be biased by how the product is marketed, for example due to the selection of a particular human model in a product image.
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects
Several recent works have considered the problem of generating reviews (or {`}tips{'}) as a form of explanation as to why a recommendation might match a customer{'}s interests.
Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation
Experiments on both the multi-domain and the single domain dialogue state tracking dataset show that our model not only scales easily with the increasing number of pre-defined domains and slots but also reaches the state-of-the-art performance.
Ranked #14 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
Generating Personalized Recipes from Historical User Preferences
Existing approaches to recipe generation are unable to create recipes for users with culinary preferences but incomplete knowledge of ingredients in specific dishes.
Ranked #1 on
Recipe Generation
on Food.com
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering
In this paper we propose a retriever-reader model that learns to attend on essential terms during the question answering process.
Multiple-choice
Multiple Choice Question Answering (MCQA)
+2
Personalized Review Generation By Expanding Phrases and Attending on Aspect-Aware Representations
In this paper, we focus on the problem of building assistive systems that can help users to write reviews.
Estimating Reactions and Recommending Products with Generative Models of Reviews
Natural language approaches that model information like product reviews have proved to be incredibly useful in improving the performance of such methods, as reviews provide valuable auxiliary information that can be used to better estimate latent user preferences and item properties.
