-
COLING 20222022Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context limits the ability of a model to learn representations that generalize to natural perturbations seen during inference. In this paper we propose a framework that incorporates
-
SIGIR 20222022Useful tips extracted from product reviews assist customers to take a more informed purchase decision, as well as making a better, easier, and safer usage of the product. In this work we argue that extracted tips should be examined based on the amount of support and opposition they receive from all product reviews. A classifier, developed for this purpose, determines the degree to which a tip is supported
-
COLING 20222022We present LANTERN, a multi-stage transformer architecture for named-entity recognition (NER) designed to operate on indefinitely large text sequences (i.e. >> 512 elements). For a given image of a form with structured text, our method uses language and spatial features to predict the entity tags of each text element. It breaks the quadratic computational constraints of the attention mechanism by operating
-
AMIA 20222022Medical coding is a complex task, requiring assignment of a subset of over 72,000 ICD codes to a patient’s notes. Modern natural language processing approaches to these tasks have been challenged by the length of the input and size of the output space. We limit our model inputs to a small window around medical entities found in our documents. From those local contexts, we build contextualized representations
-
SIGDIAL 20222022Embodied agents need to be able to interact in natural language-understanding task descriptions and asking appropriate follow up questions to obtain necessary information to be effective at successfully accomplishing tasks for a wide range of users. In this work, we propose a set of dialog acts for modelling such dialogs and annotate the TEACh dataset that includes over 3,000 situated, task oriented conversations
Related content
-
December 13, 2022Amazon Machine Learning Fellow Jiao Sun works on strategies to control text generation.
-
December 08, 2022Test set includes 1,150 text segments, each in nine languages.
-
December 07, 2022For maximum utility, says Miguel Ballesteros, large language models will need to generate coherent and consistent outputs and recognize prompts expressed in different ways.
-
December 06, 2022Familiar topics like information extraction and question answering share space with robotics and geolocation learning, and query rewriting emerges as a dynamic area of research.
-
December 05, 2022New language data will find immediate adoption by Barcelona Supercomputing Center.
-
December 05, 2022Accounting for data heterogeneity across edge devices enables more useful model updates, both locally and globally.