Taiwan

In recent years, research on image caption generation has evolved to include not only the generation based on the information obtained from an image, but also the generation based on the user’s interest to image content by providing additional information called control signals. In this study, we propose a method that considers tracing an image as a control signal and reflects the user&#39;s intention in tracing in the generation of sentences. The proposed method is characterized by the fact that it not only generates a caption according to the object to be traced, but also considers the amount of time the user has traced a specific object in the image as a control signal that expresses the user&#39;s interest on the object. In order to generate sentences whose length is proportional to the tracing time, a non-autoregressive caption generation method is employed. Comparing the proposed method with existing methods for caption generation, the image caption generation that interactively reflects the intent of the explainer using the proposed method successfully generates captions that reflect the order and details of the explanation.

IJCNLP-AACL 2022

Caption Generation Reflecting the Intent of the Explainer by Tracing on an Image

multimodal information

controllable image captioning

caption generation

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

In recent years, research on image caption generation has evolved to include not only the generation based on the information obtained from an image, but also the generation based on the user’s interest to image content by providing additional information called control signals. In this study, we propose a method that considers tracing an image as a control signal and reflects the user's intention in tracing in the generation of sentences. The proposed method is characterized by the fact that it not only generates a caption according to the object to be traced, but also considers the amount of time the user has traced a specific object in the image as a control signal that expresses the user's interest on the object. In order to generate sentences whose length is proportional to the tracing time, a non-autoregressive caption generation method is employed. Comparing the proposed method with existing methods for caption generation, the image caption generation that interactively reflects the intent of the explainer using the proposed method successfully generates captions that reflect the order and details of the explanation.

workshop paper

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 
<br>
<br>

A registration is required to access this event. Access to the event site will be granted to all registered attendees on **November 16th**. If you have not already done so, please register using the link below:
<br>
<br>https://conference.iis.sinica.edu.tw/servlet/Register?ConferenceID=411

Registration Is Required

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 

The distinction between mass nouns and count nouns has a long history in formal semantics, and linguists have been trying to identify the semantic properties defining the two classes. However, they also recognized that both can undergo meaning shifts and be used in contexts of a different type, via nominal coercion.
In this study, we present an approach to measure the meaning shift in count-mass coercion in English that makes use of static and contextualized word embedding distance. Our results show that the coercion shifts are detected only by a small subset of the traditional word embedding models and that the shifts detected by the contextualized embedding of BERT are more pronounced for mass nouns.

Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings.

We present a Japanese morphological corpus of sentences from 27 specialized domains for the two tasks of word segmentation and partof-speech tagging. Experiments on the corpus demonstrated that recent neural models with domain adaptation techniques and pretrained language models achieved accurate performance for the two tasks for many specialized domains

A Japanese Corpus of Many Specialized Domains for Word Segmentation and Part-of-Speech Tagging

Transformer-based language models are often trained on structured text where non-lexical markers of sentence and discourse structure (e.g., punctuation and casing) are present and used consistently. Transformers encode these markers and arguably benefit from the information they convey. Yet, a systematic evaluations of the contribution of non-lexical markers to model performance, and of whether models' behavior changes significantly in their absence, is currently lacking. This knowledge is both relevant from a theoretical standpoint, but also important to understand how well pretrained models may perform in common application scenarios where casing and punctuation are absent or inconsistent. 
Here, we analyze GPT-2's language modeling behavior in parallel corpora that differ in the presence vs. absence of consistent punctuation and casing. We compute GPT-2's precision and uncertainty in next-token prediction for multiple context sizes, and compare the resulting performance distributions across corpora. We find that absence of non-lexical markers, especially punctuation, increases model uncertainty, and it affects (but does not catastrophically disrupt) GPT-2's precision in next-token prediction. Interestingly, the absence of non-lexical markers prevents the model from benefiting from larger contexts in order to reduce the uncertainty of its predictions. Future work will extend this paradigm to a wider range of models and systematically investigate how features of training text affect both language modeling and downstream predictive performance.

Evaluating the role of non-lexical markers in GPT-2’s language modeling behavior

From COMET to COMES – Can Summary Evaluation Benefit from Translation Evaluation?

Random Text Perturbations Work, but not Always

Fractality of sentiment arcs for literary quality assessment: The case of Nobel laureates

Determining the origin of a given passage in rabbinic ontologies such as medieval midrash collections is not always straightforward and is often a matter of dispute among scholars, yet it is essential for scholars' understanding of the passage and its relationship to other texts in the rabbinic corpus. 

To help solve this problem, we propose a system for classification of rabbinic literature based on its style, leveraging recently released pretrained Transformer models for Hebrew. By combining our model with a text reuse engine, we demonstrate how our method can be applied to uncover lost material from the Tanhuma-Yelammedenu literature.

Style Classification of Rabbinic Literature for Detection of Lost Midrash Tanhuma Material

Large pre-trained language models have brought remarkable progress in NLP. Pre-training and Fine-tuning have given state-of- art performance across tasks in text processing. Data Augmentation techniques have also helped build state-of-art models on low or zero resource tasks. Many works in the past have attempted at learning a single massively- multilingual machine translation model for zero-shot translation. Although those translation models are producing correct translations, the main challenge is those models are producing the wrong languages for zero-shot translation. This work and its results indicate that prompt conditioned large models do not suffer from off-target language errors i.e. errors arising due to translation to wrong languages. We empirically demonstrate the effectiveness of self-supervised pre-training and data augmentation for zero-shot multi-lingual machine translation.

MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translation

We introduce a method for analyzing the relationship between internal representations of models and intermediate results by using simple math problems.

Tracing and Manipulating Intermediate Results in Neural Math Problem Solvers

Recent studies have reported that neural reasoning improves its accuracy when generating the intermediate reasoning steps. However, it is yet unclear what factors lead to such benefits.
We investigate and factorize the benefit of generating intermediate steps for symbolic reasoning.
Specifically, we decomposed the reasoning strategy regarding step granularity and chaining strategy. 
With a purely symbolic numerical reasoning dataset (e.g., A=1, B=3, C=A+3, C?), we found that the choice of reasoning strategies significantly affects the performance, with the gap becoming even larger as the extrapolation length becomes longer.
Surprisingly, we also found that certain configurations lead to nearly perfect performance, even in the case of length extrapolation.
Our results indicate the importance of further exploring effective strategies for neural reasoning models.

Caption Generation Reflecting the Intent of the Explainer by Tracing on an Image

Downloads

Next from IJCNLP-AACL 2022

Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings.

Similar lecture

Geo-Aware Image Caption Generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Caption Generation Reflecting the Intent of the Explainer by Tracing on an Image

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from IJCNLP-AACL 2022

Exploring Nominal Coercion in Semantic Spaces with Static and Contextualized Word Embeddings.

Similar lecture

Geo-Aware Image Caption Generation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads