Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userTransformer-based Lexically Constrained Headline Generation
توليد العناوين المعتمد على أساس محول
188
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تستكشف هذه الورقة متغيرا من أساليب جيلات العناوين التلقائية، حيث يلزم وجود عنوان تم إنشاؤه لتضمين عبارة معينة مثل الشركة أو اسم المنتج. الأساليب السابقة باستخدام النماذج القائمة على المحولات تولد عنوانا يتضمن عبارة معينة من خلال توفير التشفير مع معلومات إضافية مقابلة العبارة المحددة. ومع ذلك، لا يمكن أن تتضمن هذه الأساليب دائما العبارة في العنوان الذي تم إنشاؤه. مستوحاة من الأساليب السابقة القائمة على RNN توليد تسلسل رمزي في الاتجاهات الخلفية والأمام من العبارة المعينة، نقترح طريقة بسيطة قائمة على المحولات التي تضمن تضمين العبارة المحددة في العنوان الرفيع الناتج عن الجودة. ونحن ننظر أيضا في استراتيجية توليد عنوان جديدة تستفيد من ترتيب الجيل القابل للتحكم في المحولات. توضح تجاربنا مع Corpus الأخبار اليابانية أن أساليبنا، التي تضمن إدراج العبارة في العنوان الرئيسي، وتحقيق درجات Rouge مماثلة للأساليب السابقة القائمة على المحولات. نوضح أيضا أن استراتيجية توليدنا تؤدي أفضل من الاستراتيجيات السابقة.
This paper explores a variant of automatic headline generation methods, where a generated headline is required to include a given phrase such as a company or a product name. Previous methods using Transformer-based models generate a headline including a given phrase by providing the encoder with additional information corresponding to the given phrase. However, these methods cannot always include the phrase in the generated headline. Inspired by previous RNN-based methods generating token sequences in backward and forward directions from the given phrase, we propose a simple Transformer-based method that guarantees to include the given phrase in the high-quality generated headline. We also consider a new headline generation strategy that takes advantage of the controllable generation order of Transformer. Our experiments with the Japanese News Corpus demonstrate that our methods, which are guaranteed to include the phrase in the generated headline, achieve ROUGE scores comparable to previous Transformer-based methods. We also show that our generation strategy performs better than previous strategies.
References used
https://aclanthology.org/
rate research
Read More
Inspired by Curriculum Learning, we propose a consecutive (i.e., image-to-text-to-text) generation framework where we divide the problem of radiology report generation into two steps. Contrary to generating the full radiology report from the image at
once, the model generates global concepts from the image in the first step and then reforms them into finer and coherent texts using transformer-based architecture. We follow the transformer-based sequence-to-sequence paradigm at each step. We improve upon the state-of-the-art on two benchmark datasets.
We perform neural machine translation of sentence fragments in order to create large amounts of training data for English grammatical error correction. Our method aims at simulating mistakes made by second language learners, and produces a wider rang
e of non-native style language in comparison to a state-of-the-art baseline model. We carry out quantitative and qualitative evaluation. Our method is shown to outperform the baseline on data with a high proportion of errors.
Transformer has achieved great success in the NLP field by composing various advanced models like BERT and GPT. However, Transformer and its existing variants may not be optimal in capturing token distances because the position or distance embeddings
used by these methods usually cannot keep the precise information of real distances, which may not be beneficial for modeling the orders and relations of contexts. In this paper, we propose DA-Transformer, which is a distance-aware Transformer that can exploit the real distance. We propose to incorporate the real distances between tokens to re-scale the raw self-attention weights, which are computed by the relevance between attention query and key. Concretely, in different self-attention heads the relative distance between each pair of tokens is weighted by different learnable parameters, which control the different preferences on long- or short-term information of these heads. Since the raw weighted real distances may not be optimal for adjusting self-attention weights, we propose a learnable sigmoid function to map them into re-scaled coefficients that have proper ranges. We first clip the raw self-attention weights via the ReLU function to keep non-negativity and introduce sparsity, and then multiply them with the re-scaled coefficients to encode real distance information into self-attention. Extensive experiments on five benchmark datasets show that DA-Transformer can effectively improve the performance of many tasks and outperform the vanilla Transformer and its several variants.
This paper describes the system of our team (NHK) for the WAT 2021 Japanese-English restricted machine translation task. In this task, the aim is to improve quality while maintaining consistent terminology for scientific paper translation. This task
has a unique feature, where some words in a target sentence are given in addition to a source sentence. In this paper, we use a lexically-constrained neural machine translation (NMT), which concatenates the source sentence and constrained words with a special token to input them into the encoder of NMT. The key to the successful lexically-constrained NMT is the way to extract constraints from a target sentence of training data. We propose two extraction methods: proper-noun constraint and mistranslated-word constraint. These two methods consider the importance of words and fallibility of NMT, respectively. The evaluation results demonstrate the effectiveness of our lexical-constraint method.
Despite the recent advances in applying pre-trained language models to generate high-quality texts, generating long passages that maintain long-range coherence is yet challenging for these models. In this paper, we propose DiscoDVT, a discourse-aware
discrete variational Transformer to tackle the incoherence issue. DiscoDVT learns a discrete variable sequence that summarizes the global structure of the text and then applies it to guide the generation process at each decoding step. To further embed discourse-aware information into the discrete latent representations, we introduce an auxiliary objective to model the discourse relations within the text. We conduct extensive experiments on two open story generation datasets and demonstrate that the latent codes learn meaningful correspondence to the discourse structures that guide the model to generate long texts with better long-range coherence.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
