Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNeural Attention-Aware Hierarchical Topic Model
نموذج موضوع الاهتمام العصبي
291
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
نماذج الموضوعات العصبية (NTMS) تطبيق الشبكات العصبية العميقة إلى نمذجة الموضوعات. على الرغم من نجاحها، تجاهل NTMS عموما جائبا مهمين: (1) فقط يتم استخدام معلومات عدد الكلمات على مستوى المستند للتدريب، في حين يتم تجاهل المزيد من المعلومات ذات المستوى الجميل على مستوى الجملة، و (2) المعرفة الدلالية الخارجية فيما يتعلق بالوثائق، الجمل والكلمات لم يتم استغلالها للتدريب. لمعالجة هذه المشكلات، نقترح نموذج NTM (VAE) AutoNCoder (VAE) بشكل مشترك إعادة بناء الجملة وكلمة الوثيقة التي تهمها مجموعات من المبيعات الموضعية في كيس الكلمات (القوس) و EMBEDDINGS الدلالي المدرب مسبقا. يتم تحويل المدينات المدربة مسبقا لأول مرة إلى مساحة موضة كامنة مشتركة لمواءمة دلالاتها مع تضمين القوس. يتميز نموذجنا أيضا باختلاف KL هرمي للاستفادة من تضمينات كل وثيقة لتوسيع نطاق جملهم، مما يدفع المزيد من الاهتمام للجمل ذات الصلة الدولى. أظهرت كل من التجارب الكمية والنوعية فعالية نموذجنا في 1) خفض أخطاء إعادة الإعمار على كل من المستويات الجملة والوثائق، و 2) اكتشاف موضوعات أكثر تماسكا من مجموعات بيانات العالم الحقيقي.
Neural topic models (NTMs) apply deep neural networks to topic modelling. Despite their success, NTMs generally ignore two important aspects: (1) only document-level word count information is utilized for the training, while more fine-grained sentence-level information is ignored, and (2) external semantic knowledge regarding documents, sentences and words are not exploited for the training. To address these issues, we propose a variational autoencoder (VAE) NTM model that jointly reconstructs the sentence and document word counts using combinations of bag-of-words (BoW) topical embeddings and pre-trained semantic embeddings. The pre-trained embeddings are first transformed into a common latent topical space to align their semantics with the BoW embeddings. Our model also features hierarchical KL divergence to leverage embeddings of each document to regularize those of their sentences, paying more attention to semantically relevant sentences. Both quantitative and qualitative experiments have shown the efficacy of our model in 1) lowering the reconstruction errors at both the sentence and document levels, and 2) discovering more coherent topics from real-world datasets.
References used
https://aclanthology.org/
rate research
Read More
Earning calls are among important resources for investors and analysts for updating their price targets. Firms usually publish corresponding transcripts soon after earnings events. However, raw transcripts are often too long and miss the coherent str
ucture. To enhance the clarity, analysts write well-structured reports for some important earnings call events by analyzing them, requiring time and effort. In this paper, we propose TATSum (Template-Aware aTtention model for Summarization), a generalized neural summarization approach for structured report generation, and evaluate its performance in the earnings call domain. We build a large corpus with thousands of transcripts and reports using historical earnings events. We first generate a candidate set of reports from the corpus as potential soft templates which do not impose actual rules on the output. Then, we employ an encoder model with margin-ranking loss to rank the candidate set and select the best quality template. Finally, the transcript and the selected soft template are used as input in a seq2seq framework for report generation. Empirical results on the earnings call dataset show that our model significantly outperforms state-of-the-art models in terms of informativeness and structure.
When developing topic models, a critical question that should be asked is: How well will this model work in an applied setting? Because standard performance evaluation of topic interpretability uses automated measures modeled on human evaluation test
s that are dissimilar to applied usage, these models' generalizability remains in question. In this paper, we probe the issue of validity in topic model evaluation and assess how informative coherence measures are for specialized collections used in an applied setting. Informed by the literature, we propose four understandings of interpretability. We evaluate these using a novel experimental framework reflective of varied applied settings, including human evaluations using open labeling, typical of applied research. These evaluations show that for some specialized collections, standard coherence measures may not inform the most appropriate topic model or the optimal number of topics, and current interpretability performance validation methods are challenged as a means to confirm model quality in the absence of ground truth data.
Cross-attention is an important component of neural machine translation (NMT), which is always realized by dot-product attention in previous methods. However, dot-product attention only considers the pair-wise correlation between words, resulting in
dispersion when dealing with long sentences and neglect of source neighboring relationships. Inspired by linguistics, the above issues are caused by ignoring a type of cross-attention, called concentrated attention, which focuses on several central words and then spreads around them. In this work, we apply Gaussian Mixture Model (GMM) to model the concentrated attention in cross-attention. Experiments and analyses we conducted on three datasets show that the proposed method outperforms the baseline and has significant improvement on alignment quality, N-gram accuracy, and long sentence translation.
We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers. Our approach builds on existing losses that encourage attention maps in neural sequence-to-sequence models to imitate the output of cla
ssical word alignment algorithms. Where past work has used word-level alignments, we focus on spans; borrowing ideas from phrase-based machine translation, we align subtrees in semantic parses to spans of input sentences, and encourage neural attention mechanisms to mimic these alignments. This method improves the performance of transformers, RNNs, and structured decoders on three benchmarks of compositional generalization.
Unlike well-structured text, such as news reports and encyclopedia articles, dialogue content often comes from two or more interlocutors, exchanging information with each other. In such a scenario, the topic of a conversation can vary upon progressio
n and the key information for a certain topic is often scattered across multiple utterances of different speakers, which poses challenges to abstractly summarize dialogues. To capture the various topic information of a conversation and outline salient facts for the captured topics, this work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task. The proposed contrastive objectives are framed as auxiliary tasks for the primary dialogue summarization task, united via an alternative parameter updating strategy. Extensive experiments on benchmark datasets demonstrate that the proposed simple method significantly outperforms strong baselines and achieves new state-of-the-art performance. The code and trained models are publicly available via .
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
