In this paper, we describe the development of a communication support sy...
Using large language models (LLMs) for source code has recently gained
a...
Automation of dialogue system evaluation is a driving force for the effi...
Although a machine translation model trained with a large in-domain para...
Prior studies addressing target-oriented conversational tasks lack a cru...
Avoiding the generation of responses that contradict the preceding conte...
Short answer scoring (SAS) is the task of grading short text written by ...
In the perspective of a layer normalization (LN) position, the architect...
Ensembling is a popular method used to improve performance as a last res...
Natural language processing technology has rapidly improved automated
gr...
Most current machine translation models are mainly trained with parallel...
Interpretable rationales for model predictions are crucial in practical
...
Position representation is crucial for building position-aware
represent...
Text-to-SQL is a crucial task toward developing methods for understandin...
We review the EfficientQA competition from NeurIPS 2020. The competition...
Understanding the influence of a training instance on a neural network m...
Neural Machine Translation (NMT) has shown drastic improvement in its qu...
Despite the current diversity and inclusion initiatives in the academic
...
Existing approaches for grammatical error correction (GEC) largely rely ...
In general, the labels used in sequence labeling consist of different ty...
This paper investigates how to effectively incorporate a pre-trained mas...
Model ensemble techniques often increase task performance in neural netw...
We examine a methodology using neural language models (LMs) for analyzin...
One key principle for assessing semantic similarity between texts is to
...
Interpretable rationales for model predictions play a critical role in
p...
Existing automatic evaluation metrics for open-domain dialogue response
...
Filtering noisy training data is one of the key approaches to improving ...
Recent machine translation algorithms mainly rely on parallel corpora.
H...
The writing process consists of several stages such as drafting, revisin...
Many text generation tasks naturally contain two steps: content selectio...
Language technologies play a key role in assisting people with their wri...
The incorporation of pseudo data in the training of grammatical error
co...
This paper proposes a novel Recurrent Neural Network (RNN) language mode...
Knowledge discovery from GPS trajectory data is an important topic in se...
The current success of deep neural networks (DNNs) in an increasingly br...
In this paper, we propose a new kernel-based co-occurrence measure that ...
This paper proposes a state-of-the-art recurrent neural network (RNN)
la...
Following great success in the image processing field, the idea of
adver...
The encoder-decoder model is widely used in natural language generation
...
This paper proposes a reinforcing method that refines the output layers ...
To analyze the limitations and the future directions of the extractive
s...
This paper tackles the reduction of redundant repeating generation that ...