Page 66 - Read Online

Page 259 Su et al. Intell Robot 2022;2(3):244­74 I http://dx.doi.org/10.20517/ir.2022.17

Duetotheusefulnessofcausalmodeling [10] , removingdiscriminationforrecommendersystemsfromacausal
perspective has attracted increasing attention, where the cause graph is used for exposing potentially causal re-
lationships from data. On the one hand, most discrimination can be understood with additional confounding
factors in the causal graph and the effect of discrimination can also be inferred through the causal graph. On
the other hand, recommendation can be considered as an intervention, which is similar to treating a patient
with a specific drug, requiring counterfactual reasoning. What happens when recommending certain items
to the users? The causal model has the potential to answer this question. For example, Wu et al. [68] focused
on fairness-aware ranking and proposed to use path-specific effects to detect and remove the direct and indi-
rect rank discrimination. Zhao et al. [69] and Zheng et al. [70] considered the effect of item popularity on user
behavior and intervened in the item popularity to make fair recommendations. Zhang et al. [71] attributed pop-
ularity bias in the recommender systems to the undesirable causal effect of item popularity on items exposure
and suggested intervening in the distribution of the exposed items to eliminate this causal effect. Wang et
al. [72] leveraged counterfactual reasoning to eliminate the causal effect of exposure features on the prediction.
Li et al. [73] proposed generating embedding vectors independent of sensitive attributes by adversarial learn-
ing to achieve counterfactual fairness. Huang et al. [74] regarded causal inference as bandits and performed
-operator to simulate the arm selection strategy to achieve fairness towards individuals.

Nowadays, the explainability of recommender systems is increasingly important, which improves the persua-
siveness and trustworthiness of recommendations. When addressing the fairness issues of recommender sys-
tems from the causal perspective, the explanation of recommendations can also be provided from the effects
transmittedalongthecausalpaths. Thus, weareconfidentthatcausalmodelingwillbringtherecommendation
research into a new frontier.

6.3. Fair natural language processing
Natural language processing (NLP) is an important technology for machines to understand and interpret hu-
man natural language text and realize human–computer interaction. With the development and evolution of
human natural language, the natural language is characterized by a certain degree of gender, ethnicity, region,
and culture. These characteristics are sensitive in certain situations, and inappropriate use can lead to preju-
dice and discrimination. For example, Zhao et al. [75] found that the datasets associated with multi-label object
classification and visual semantic role labeling exhibit discrimination towards gender attribute, and, unfortu-
nately, the model trained with these data would further amplify the disparity. Stanovsky et al. [76] provided
multilingual quantitative evidence of gender bias in large-scale translation. They found that, among the eight
target languages, all four business systems and two academic translation systems tend to translate according
to stereotype rather than context. Huang et al. [77] used counterfactual evaluations to investigate whether and
how language models are affected by sensitive attributes (e.g., country, occupation, and gender) to generate
sentiment bias. Specifically, they used individual fairness metrics and group fairness metrics to measure coun-
terfactual sentiment bias, conducted model training on news articles and Wikipedia corpus, and showcased
the existence of sentiment bias.

Fair NLP is a kind of NLP without bias or discrimination with sensitive attributes. Shin et al. [78] proposed a
counterfactual reasoning method for eliminating the gender bias of word embedding, which aims to disentan-
gle a latent space of a given word embedding into two disjoint encoded latent spaces, namely the gender latent
space and the semantic latent space, to achieve disentanglement of semantic and gender implicit descriptions.
To this end, they used a gradient reversal layer to prohibit the inference about the gender latent information
fromsemanticinformation. Then,theygeneratedacounterfactualwordembeddingbyconvertingtheencoded
gender into the opposite gender and used it to produce a gender-neutralized word embedding after geometric
alignment regularization. As such, the word embedding generated by this method can strike a balance be-
tween gender debiasing and semantic information preserving. Yang and Feng [79] presented a causality-based
post-processing approach for eliminating the gender bias in word embeddings. Specifically, their method was