In multimodal understanding tasks, visual and linguistic ambiguities can arise. Visual ambiguity can occur when visual objects require a model to ground a referring expression in a video without strong supervision, while linguistic ambiguity can occur from changes in entities in action flows. As an example from the cooking domain, “oil” mixed with “salt” and “pepper” could later be referred to as a “mixture”. Without a clear visual-linguistic alignment, we cannot know which among several objects shown is referred to by the language expression “mixture”, and without resolved antecedents, we cannot pinpoint what the mixture is. We define this chicken-and-egg problem as Visual-linguistic Ambiguity. In this paper, we present Find2Find, a joint anaphora resolution and object localization dataset targeting the problem of visual-linguistic ambiguity, consisting of 500 anaphora-annotated recipes with corresponding videos. We present experimental results of a novel end-to-end joint multitask learning framework for Find2Find that fuses visual and textual information and shows improvements both for anaphora resolution and object localization with one joint model in multitask learning, as compared to a strong single-task baseline.

In several ASR use cases, training and adaptation of domain-specific LMs can only rely on a small amount of manually verified text transcriptions and sometimes a limited amount of in-domain speech. Training of LSTM LMs in such limited data scenarios can benefit from alternate uncertain ASR hypotheses, as observed in our recent work. In this paper, we propose a method to train Transformer LMs on ASR confusion networks. We evaluate whether these self-attention based LMs are better at exploiting alternate ASR hypotheses as compared to LSTM LMs. Evaluation results show that Transformer LMs achieve 3-6% relative reduction in perplexity on the AMI scenario meetings but perform similar to LSTM LMs on the smaller Verbmobil conversational corpus. Evaluation on ASR N-best rescoring shows that LSTM and Transformer LMs trained on ASR confusion networks do not bring significant WER reductions. However, a qualitative analysis reveals that they are better at predicting less frequent words.

In recent years, voice-controlled personal assistants have revolutionized the interaction with smart devices and mobile applications. The collected data are then used by system providers to train language models (LMs). Each spoken message reveals personal information, hence removing private information from the input sentences is necessary. Our data sanitization process relies on recognizing and replacing named entities by other words from the same class. However, this may harm LM training because privacy-transformed data is unlikely to match the test distribution. This paper aims to fill the gap by focusing on the adaptation of LMs initially trained on privacy-transformed sentences using a small amount of original untransformed data. To do so, we combine class-based LMs, which provide an effective approach to overcome data sparsity in the context of n-gram LMs, and neural LMs, which handle longer contexts and can yield better predictions. Our experiments show that training an LM on privacy-transformed data result in a relative 11% word error rate (WER) increase compared to training on the original untransformed data, and adapting that model on a limited amount of original untransformed data leads to a relative 8% WER improvement over the model trained solely on privacy-transformed data.

Linguistic ambiguities arising from changes in entities in action flows are a key challenge in instructional cooking videos. In particular, temporally evolving entities present rich and to date understudied challenges for anaphora resolution. For example “oil” mixed with “salt” is later referred to as a “mixture”. In this paper we propose novel annotation guidelines to annotate recipes for the anaphora resolution task, reflecting change in entities. Moreover, we present experimental results for end-to-end multimodal anaphora resolution with the new annotation scheme and propose the use of temporal features for performance improvement.

Hyperpartisan news is news that takes an extreme left-wing or right-wing standpoint. If one is able to reliably compute this meta information, news articles may be automatically tagged, this way encouraging or discouraging readers to consume the text. It is an open question how successfully hyperpartisan news detection can be automated, and the goal of this SemEval task was to shed light on the state of the art. We developed new resources for this purpose, including a manually labeled dataset with 1,273 articles, and a second dataset with 754,000 articles, labeled via distant supervision. The interest of the research community in our task exceeded all our expectations: The datasets were downloaded about 1,000 times, 322 teams registered, of which 184 configured a virtual machine on our shared task cloud service TIRA, of which in turn 42 teams submitted a valid run. The best team achieved an accuracy of 0.822 on a balanced sample (yes : no hyperpartisan) drawn from the manually tagged corpus; an ensemble of the submitted systems increased the accuracy by 0.048.