Relative Improvement

Motivated by the success of ensemble methods in machine learning and other areas of natu- ral language processing, we developed a multi- strategy and multi-source approach to question answering which …...

The use of pivot languages and word- alignment techniques over bilingual cor- pora has proved an effective approach for extracting paraphrases of words and short phrases. However, inherent ambiguities in …...

AbstractThe multi-level adaptive networks (MLAN) technique is a cross-lingual adaptation framework where a bottleneck (BN) layer in a deep neural network (DNN) trained in a source language is used for …...

AbstractA trend to digitize historical paper-based archives has emerged in recent years, with the advent of digital optical scanners. A lot of paper-based books, textbooks, magazines, articles, and documents are …...

AbstractWe present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the …...

AbstractRecent graph-based models for joint multiple intent detection and slot filling have obtained promising results through modeling the guidance from the prediction of intents to the decoding of slot filling. …...

AbstractWhen primed with only a handful of training samples, very large, pretrained language models such as GPT-3 have shown competitive results when compared to fully-supervised, fine-tuned, large, pretrained language models. …...

AbstractKnowledge base completion (KBC) has benefitted greatly by learning explainable rules in an human-interpretable dialect such as first-order logic. Rule-based KBC has so far, mainly focussed on learning one of …...

AbstractClass imbalance problem can cause machine learning models to produce an undesirable performance on the minority class as well as the whole dataset. Using data augmentation techniques to increase the …...

AbstractDespite the surprising few-shot performance of in-context learning (ICL), it is still a common practice to randomly sample examples to serve as context. This paper advocates a new principle for …...