Thailand

Video Question Answering is a task which requires an AI agent to answer questions grounded in video. This task entails three key challenges: (1) understand the intention of various questions, (2) capturing various elements of the input video (e.g., object, action, causality), and (3) cross-modal grounding between language and vision information. We propose Motion-Appearance Synergistic Networks (MASN), which embed two cross-modal features grounded on motion and appearance information and selectively utilize them depending on the question&#39;s intentions. 
MASN consists of a motion module, an appearance module, and a motion-appearance fusion module. The motion module computes the action-oriented cross-modal joint representations, while the appearance module focuses on the appearance aspect of the input video. Finally, the motion-appearance fusion module takes each output of the motion module and the appearance module as input, and performs question-guided fusion. As a result, MASN achieves new state-of-the-art performance on the TGIF-QA and MSVD-QA datasets. We also conduct qualitative analysis by visualizing the inference results of MASN.

ACL-IJCNLP 2021

Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering

language grounding to vision

multi-modal reasoning

video question answering

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

Video Question Answering is a task which requires an AI agent to answer questions grounded in video. This task entails three key challenges: (1) understand the intention of various questions, (2) capturing various elements of the input video (e.g., object, action, causality), and (3) cross-modal grounding between language and vision information. We propose Motion-Appearance Synergistic Networks (MASN), which embed two cross-modal features grounded on motion and appearance information and selectively utilize them depending on the question's intentions. 
MASN consists of a motion module, an appearance module, and a motion-appearance fusion module. The motion module computes the action-oriented cross-modal joint representations, while the appearance module focuses on the appearance aspect of the input video. Finally, the motion-appearance fusion module takes each output of the motion module and the appearance module as input, and performs question-guided fusion. As a result, MASN achieves new state-of-the-art performance on the TGIF-QA and MSVD-QA datasets. We also conduct qualitative analysis by visualizing the inference results of MASN.

poster

Understanding the multi-scale visual information
in a video is essential for Video Question Answering (VideoQA).
Therefore, we propose a novel Multi-Scale Progressive Attention Network 
(MSPAN)
to achieve relational reasoning between cross-scale video information.
We construct clips of different lengths to represent different 
scales of the video.
Then, the clip-level features are aggregated into node features 
by using max-pool, 
and a graph is generated for each scale of clips.
For cross-scale feature interaction, 
we design a message passing strategy between adjacent scale graphs, 
i.e., top-down scale interaction and bottom-up scale interaction.
Under the question's guidance of progressive attention, 
we realize the fusion of all-scale video features.
Experimental evaluations on three
benchmarks: TGIF-QA, MSVD-QA and MSRVTT-QA show
our method has achieved state-of-the-art performance.

Multi-Scale Progressive Attention Network for Video Question Answering

Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source. However, such retrieval models often require large memory to run because of the massive size of their passage index. In this paper, we introduce Binary Passage Retriever (BPR), a memory-efficient neural retrieval model that integrates a learning-to-hash technique into the state-of-the-art Dense Passage Retriever (DPR) to represent the passage index using compact binary codes rather than continuous vectors. BPR is trained with a multi-task objective over two tasks: efficient candidate generation based on binary codes and accurate reranking based on continuous vectors. Compared with DPR, BPR substantially reduces the memory cost from 65GB to 2GB without a loss of accuracy on two standard open-domain question answering benchmarks: Natural Questions and TriviaQA. Our code and trained models are available at https://github.com/studio-ousia/bpr.

Efficient Passage Retrieval with Hashing for Open-domain Question Answering

We present a new human-human dialogue dataset - PhotoChat, the first dataset that casts light on the photo sharing behavior in online messaging. PhotoChat contains 12k dialogues, each of which is paired with a user photo that is shared during the conversation. Based on this dataset, we propose two tasks to facilitate research on image-text modeling: a photo-sharing intent prediction task that predicts whether one intends to share a photo in the next conversation turn, and a photo retrieval task that retrieves the most relevant photo according to the dialogue context. In addition, for both tasks, we provide baseline models using the state-of-the-art models and report their benchmark performances. The best image retrieval model achieves 10.4% recall@1 (out of 1000 candidates) and the best photo intent prediction model achieves 58.1% F1 score, indicating that the dataset presents interesting yet challenging real-world problems. We are releasing PhotoChat to facilitate future research work among the community.

PhotoChat: A Human-Human Dialogue Dataset With Photo Sharing Behavior For Joint Image-Text Modeling

A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information. Many recent studies report improvements when equipping their models with the multimodal module, despite the controversy of whether such improvements indeed come from the multimodal part. We revisit the contribution of multimodal information in MMT by devising two interpretable MMT models. To our surprise, although our models replicate similar gains as recently developed multimodal-integrated systems achieved, 
our models learn to ignore the multimodal information. Upon further investigation, we discover that the improvements achieved by the multimodal models over text-only counterparts are in fact results of the regularization effect. 
We report empirical findings that highlight the importance of MMT models' interpretability, and discuss how our findings will benefit future research.

Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation

In this work, we describe our system submission to the SemEval 2021 Task 11: NLP Contribution Graph Challenge. We attempt all the three sub-tasks in the challenge and report our results. Subtask 1 aims to identify the contributing sentences in a given publication. Subtask 2 follows from Subtask 1 to extract the scientific term and predicate phrases from the identified contributing sentences. The final Subtask 3 entails extracting triples (subject, predicate, object) from the phrases and categorizing them under one or more defined information units. With the NLPContributionGraph Shared Task, the organizers formalized the building of a scholarly contributions-focused graph over NLP scholarly articles as an automated task. Our approaches include a BERT-based classification model for identifying the contributing sentences in a research publication, a rule-based dependency parsing for phrase extraction, followed by a CNN-based model for information units classification and a set of rules for triples extraction. The quantitative results show that we obtain the 5th, 5th, and 7th rank respectively in three evaluation phases.

INNOVATORS at SemEval-2021 Task-11: A Dependency Parsing and BERT-based model for Extracting Contribution Knowledge from Scientific Papers

In this paper, we present our text augmentation based approach for the Table Statement Support Subtask (Phase A) of SemEval-2021 Task 9. We experiment with different text augmentation techniques such as back translation and synonym swapping using Word2Vec and WordNet. We show that text augmentation techniques lead to 2.5% improvement in F1 on the test set. Further, we investigate the impact of domain adaptation and joint learning on fact verification in tabular data by utilizing the SemTabFacts and TabFact datasets. We observe that joint learning improves the F1 scores on the SemTabFacts and TabFact test sets by 3.31% and 0.77%, respectively.


BOUN at SemEval-2021 Task 9: Text Augmentation Techniques for Fact Verification in Tabular Data

In this paper, we introduce our system that we participated with at the multilingual and cross-lingual word-in-context disambiguation SemEval 2021 shared task. In our experiments, we investigated the possibility of using an all words fine-grained word sense disambiguation system trained purely on sense-annotated data in English and draw predictions on the semantic equivalence of words in context based on the similarity of the ranked lists of the (English) WordNet synsets returned for the target words decisions had to be made for. We overcame the multi,-and cross-lingual aspects of the shared task by applying a multilingual transformer for encoding the texts written in either Arabic, English, French, Russian and Chinese. While our results lag behind top scoring submissions, it has the benefit that it not only provides a binary prediction whether two words in their context have the same meaning, but also provides a more tangible output in the form of a ranked list of (English) WordNet synsets irrespective of the language of the input texts. As our framework is designed to be as generic as possible, it can be applied as a baseline for basically any language (supported by the multilingual transformed architecture employed) even in the absence of any additional form of language specific training data.

SzegedAI at SemEval-2021 Task 2: Zero-shot Approach for Multilingual and Cross-lingual Word-in-Context Disambiguation

We describe the systems used by the RoMa team in the shared task on Detecting and Rating Humor and Offense (HaHackathon) at SemEval 2021. Our systems rely on data representations learned through fine-tuned neural language models. Particularly, we explore two distinct architectures. The first one is based on a Siamese Neural Network (SNN) combined with a graph-based clustering method. The SNN model is used for learning a latent space where instances of humor and non-humor can be distinguished. The clustering method is applied to build prototypes of both classes which are used for training and classifying new messages. The second one combines neural language model representations with a linear regression model which makes the final ratings. Our systems achieved the best results for humor classification using model one, whereas for offensive and humor rating the second model obtained better performance. In the case of the controversial humor prediction, the most significant improvement was achieved by a fine-tuning of the neural language model. In general, the results achieved are encouraging and give us a starting point for further improvements.

RoMa at SemEval-2021 Task 7: A Transformer-based Approach for Detecting and Rating Humor and Offense

Understanding tables is an important and relevant task that involves understanding table structure as well as being able to compare and contrast information within cells. In this paper, we address this challenge by presenting a new dataset and tasks that addresses this goal in a shared task in SemEval 2020 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS). Our dataset contains 981 manually-generated tables and an auto-generated dataset of 1980 tables providing over 180K statement and over 16M evidence annotations. SEM-TAB-FACTS featured two sub-tasks. In sub-task A, the goal was to determine if a statement is supported, refuted or unknown in relation to a table. In sub-task B, the focus was on identifying the specific cells of a table that provide evidence for the statement. 69 teams signed up to participate in the task with 19 successful submissions to subtask A and 12 successful submissions to subtask B. We present our results and main findings from the competition.

SemEval-2021 Task 9: Fact Verification and Evidence Finding for Tabular Data in Scientific Documents (SEM-TAB-FACTS)

This paper presents a technical report of our submission to the 4th task of SemEval-2021, titled: Reading Comprehension of Abstract Meaning. In this task, we want to predict the correct answer based on a question given
a context. Usually, contexts are very lengthy and require a large receptive field from the model. Thus, common contextualized language models like BERT miss fine representation and performance due to the limited capacity of the input tokens. To tackle this problem, we used the longformer model to better process the sequences. Furthermore, we utilized the method proposed in the longformer benchmark on wikihop dataset which improved the accuracy on our task data from (23.01% and 22.95%) achieved by the baselines for subtask 1 and 2, respectively, to (70.30% and 64.38%).

Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering

Downloads

Next from ACL-IJCNLP 2021

Multi-Scale Progressive Attention Network for Video Question Answering

Similar lecture

Multi-Scale Progressive Attention Network for Video Question Answering